Artificial intelligence / machine learning configuration and security

Abstract

Methods for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, are disclosed herein. Corresponding systems and apparatuses are also disclosed. The method performed by a User Equipment (UE) comprises receiving, from a 5 network node prior to activating Access Stratum, AS, security, a configuration for an AI / ML functionality. The method further comprises using the AI / ML functionality according to the received configuration to perform at least one action after the AS security mode is activated.

Description

ARTIFICIAL INTELLIGENCE / MACHINE LEARNING CONFIGURATION AND SECURITYFIELD

[0001] The present disclosure relates generally to communication systems, and more specifically to Artificial Intelligence (Al) / Machine Learning (ML) configuration and security in wireless communication networks.BACKGROUNDArtificial Intelligence (Al) / Machine Learning (ML) for Physical layer (PHY)

[0002] Artificial Intelligence (Al) and Machine Learning (ML) have been investigated, both in academia and industry, as promising tools to optimize the design of the air-interface in wireless communication networks. Example use cases include using autoencoders for Channel State Information (CSI) compression to reduce the feedback overhead and improve channel prediction accuracy; using deep neural networks for classifying Line-of-Sight (LOS) and Non- LOS (NLOS) conditions to enhance the positioning accuracy; using reinforcement learning for beam selection at the network side and / or the User Equipment (UE) side to reduce the signaling overhead and beam alignment latency; and using deep reinforcement learning to learn an optimal precoding policy for complex Multiple Input Multiple Output (MIMO) precoding problems.

[0003] In 3rd Generation Partnership Project (3GPP) New Radio (NR) standardization work, a new release 18 study item on AI / ML for the NR air interface started in May 2022. This study item explored the benefits of augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead. Through studying a few selected use cases (CSI feedback, beam management, and positioning), this study item aims at laying the foundation for future airinterface use cases leveraging AI / ML techniques. The analysis carried out during Rel. 18 is now considered in the context of a Rel. 19 work item [1]. Additionally, during Rel. 19, a new study item addressing AI / ML for mobility has been approved. In the context of this new study item, 3GPP will investigate methods for cell-level measurement predictions, and mobility event predictions (e.g., Radio Link Failure (RLF), handover failure, mobility-related events predictions such as A3 / A5) [2].SUMMARY

[0004] Various computer-implemented systems, methods, and articles of manufacture related to AI / ML configuration and security in wireless communication networks are described herein. In one embodiment, a method performed by a UE for configuring an AI / ML functionality comprises receiving, from a network node prior to activating Access Stratum, AS, security, a configuration for an AI / ML functionality. The method further comprises using the AI / ML functionality according to the received configuration to perform at least one action after the AS security mode is activated. The method may further comprise, in response to receiving the configuration for the AI / ML functionality, sending, to the network node, an indication that the configuration for the AI / ML functionality has been successfully applied, where the indication comprises a Radio Resource Control, RRC, Response message. The method may further comprise, in response to receiving the configuration for the AI / ML functionality, sending, to the network node, an applicability indication for the AI / ML functionality.

[0005] In one embodiment, a method performed by a UE for configuring an AI / ML functionality comprises receiving, from a network node after activating AS security, a configuration for an AI / ML functionality. The method further comprises using the AI / ML functionality according to the received configuration to perform at least one action. The method may further comprise receiving the configuration for the AI / ML functionality prior to activating the AS security and in response to triggering a recovery action. The method may further comprise receiving an RRC message comprising the configuration for the AI / ML functionality after the AS security is activated and triggering a recovery action in response to the RRC message not being secured. The method may further comprise logging information about at least one failure upon triggering the recovery action, and transmitting, to the network node, a report comprising the information logged about the at least one failure.

[0006] In one embodiment, a method performed by a network node for configuring an AI / ML functionality comprises sending, to a UE prior to AS security being activated at the UE, a configuration for an AI / ML functionality, where the AI / ML functionality is used by the UE according to the received configuration to perform at least one action after the AS security is activated. The method may further comprise, in response to the configuration for the AI / ML functionality, receiving, from the UE, an indication that the configuration for the AI / ML functionality has been successfully applied, wherein the indication comprises an RRC Response message. The method may further comprise, in response to the configuration for the AI / ML functionality, receiving, from the UE, an applicability indication for the AI / MLfunctionality. The method may further comprise receiving, from the UE, a report comprising the one or more predictions after the AS security is activated.

[0007] In one embodiment, a method performed by a network node for configuring an AI / ML functionality comprises sending, to a UE after activating AS security, a configuration for an AI / ML functionality, where the AI / ML functionality is used by the UE according to the received configuration to perform at least one action. The method may further comprise receiving, from the UE, information about a failure when the UE receives an unsecured RRC message including the configuration for the AI / ML functionality.

[0008] In one embodiment, a UE for configuring an AI / ML functionality, comprises processing circuitry configured to perform one or more steps comprising at least one of: receiving, from a network node prior to activating AS security, a configuration for an AI / ML functionality; and using the AI / ML functionality according to the received configuration to perform at least one action after the AS security is activated. The UE further comprises power supply circuitry configured to supply power to the processing circuitry.

[0009] In one embodiment, a UE for configuring an AI / ML functionality, comprises processing circuitry configured to perform one or more steps comprising at least one of: receiving, from a network node after activating AS security, a configuration for an AI / ML functionality; and using the AI / ML functionality according to the received configuration to perform at least one action. The UE further comprises power supply circuitry configured to supply power to the processing circuitry.

[0010] In one embodiment, a network node for configuring an AI / ML functionality, comprises processing circuitry configured to perform one or more steps comprising at least one of: sending, to a UE prior to AS security being activated at the UE, a configuration for an AI / ML functionality, wherein the AI / ML functionality is used by the UE according to the received configuration to perform at least one action after the AS security is activated. The network node further comprises power supply circuitry configured to supply power to the processing circuitry.

[0011] In one embodiment, a network node for configuring an AI / ML functionality, comprises processing circuitry configured to perform one or more steps comprising at least one of: sending, to a UE prior to AS security being activated at the UE, a configuration for an AI / ML functionality, wherein the AI / ML functionality is used by the UE according to the received configuration to perform at least one action after the AS security is activated. The network node further comprises power supply circuitry configured to supply power to the processing circuitry.BRIEF DESCRIPTION OF DRAWINGS

[0012] For a better understanding of the various described embodiments, reference should be made to the Detailed Description below, in conjunction with the following drawings in which like reference numerals refer to corresponding parts throughout the figures.

[0013] Figure 1 illustrates an example of proactive reporting of AI / ML applicability, in accordance with some embodiments.

[0014] Figure 2 illustrates an example of reactive reporting of AI / ML applicability, in accordance with some embodiments.

[0015] Figure 3 illustrates an example summary of an IDLE to CONNECTED transition of a UE, in accordance with some embodiments.

[0016] Figure 4 illustrates an example of an IDLE to CONNECTED transition in which a UE receives an RRC Reconfiguration including an AI / ML configuration before the UE receives a security mode command, in accordance with some embodiments.

[0017] Figure 5 illustrates an example of an IDLE to CONNECTED transition in which a UE transmits an RRC Response message including an applicability indication for a AI / ML functionality before it receives a security mode command, in accordance with some embodiments.

[0018] Figure 6 illustrates an example of an IDLE to CONNECTED transition in which a UE transmits an RRC Reconfiguration Complete message before security activation and a UE Assistance Information (UAI) message (e.g., RRC response) including an applicability indication for an AI / ML functionality after security is activated, in accordance with some embodiments.

[0019] Figure 7 illustrates an example of an IDLE to CONNECTED transition in which a UE receives an RRC message including an AI / ML configuration after AS security activation, in accordance with some embodiments.

[0020] Figure 8 illustrates a flowchart showing a method performed by a UE for configuring an AI / ML functionality, in accordance with some embodiments.

[0021] Figure 9 illustrates a flowchart showing a method performed by a UE for configuring an AI / ML functionality, in accordance with some embodiments.

[0022] Figure 10 illustrates a flowchart showing a method performed by a network node for configuring an AI / ML functionality, in accordance with some embodiments.

[0023] Figure 11 illustrates a flowchart showing a method performed by a network node for configuring an AI / ML functionality, in accordance with some embodiments.

[0024] Figure 12 shows an example of a communication system in accordance with some embodiments.

[0025] Figure 13 shows a UE in accordance with some embodiments.

[0026] Figure 14 shows a network node in accordance with some embodiments.

[0027] Figure 15 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized.DETAILED DESCRIPTION(1) Applicability Reporting

[0028] Applicability reporting has been discussed during the Rel.18 study item, to allow the UE to inform a network node, e.g., a gNB, about the applicability of an AI / ML model / functionality while the UE is connected to the gNB. An AI / ML model / functionality may be applicable or not depending on a number of factors, also known as applicability conditions, that are only partly under the control of the gNB. For example, whether the UE has an AI / ML model that is applicable given the current location of the UE, or given the current speed of the UE, is not something that the network can control or know, because typically it is assumed that the UE-side model is not trained and generated by the gNB. Rather, it is typically assumed that the UE-side model is trained and generated by a node outside the Radio Access Network (RAN), such as by an Over-the-Top (OTT) server or by a Core Network (CN) function controlled by the UE vendor or by the Mobile Network Operator (MNO).

[0029] Two types of applicability reporting were identified during the Rel.18 study item and are currently being discussed in RAN2 for the normative phase, the so-called reactive approach and the proactive approach, further detailed in [1].

[0030] In the proactive approach, the network enquires the UE capabilities and configures the UE to report the applicability of an AI / ML functionality and, based on the reported information, a network configures a UE with an inference configuration. Figure 1 shows an example 100 of proactive reporting of applicability. The steps are as follows. At Step 1 SI 10, the network, e.g., network node 104, sends a UECapabilityEnqiry message to initiate the procedure for a UE, e.g., UE 102, to report its supported AI / ML functionalities. At Step 2 S120, the UE sends, to the network, a UECapablitylnformation message containing supported functionalities at the UE side. At Step 3 SI 30, the network configures the UE such that it is allowed to provide its applicable AI / ML functionalities. At Step 4 S140, the UE sends applicable AI / ML functionalities to the network upon a change of an applicable AI / ML functionality / condition. At Step 5 S150, the network sends, to the UE, an inferenceconfiguration for the applicable AI / ML functionalities. At Step 6 SI 60, the inference / monitoring starts (e.g., is instantiated) based on network / UE activation / deactivation.

[0031] Figure 2 shows an example 200 of reactive reporting of AI / ML applicability. In the reactive approach, a network, e.g., network node 204, enquires a UE, e.g., UE 202, of its capabilities and configures the UE with an AI / ML functionality (possibly including an inference configuration) in response to which the UE is able to determine the applicability of the AI / ML functionality. If the configured AI / ML functionality is applicable, the functionality could be up and running as soon as possible, without the need for an additional reconfiguration. The steps are as follows. At Step 1 S210, the network sends, to the UE, a UE capability enquiry (UECapabilityEnquiry) message to initiate the procedure of the UE reporting its supported AI / ML functionalities. At Step 2 S220, the UE sends, to the network, a UE capability information (UECapablitylnformation) message containing supported functionalities at the UE side. At Step 3 S230, the network provides network configurations and initiates the UE to report its applicable functionalities. At Step 4 S240, the UE sends its applicable AI / ML functionalities to the network. At Step 5 S250, the network sends, to the UE, an updated inference configuration for applicable AI / ML functionalities reported in Step 4 S240. At Step 6 S260, the inference / monitoring starts (e.g., is instantiated) based on network / UE activation / deactivation.(2) Access Stratum (AS) Security and IDLE / CONNECTED Transition

[0032] In NR, when a UE is in an IDLE state (e.g., RRC_IDLE), the UE does not have the AS security activated (up and running). It is during the transition to a CONNECTED state that the UE initiates the AS security e.g., calculates the AS security keys for ciphering and integrity protection of control plane (for RRC messages) and user plane (for PDCP packets carrying user plane data). A summary of the IDLE to CONNECTED transition is reproduced in Figure 3, which shows an example 300 of an IDLE to CONNECTED transition and the initial security activation. An interaction between a UE (e.g., UE 302), a gNB (e.g., gNB 304), and an Access and Mobility Management Function, AMF, (e.g., AMF 306) is shown. The steps are as follows. At Step 1 S310, the UE sends, to the network / gNB (e.g., gNB 304), a request to setup a new connection from RRC_IDLE. At Step 2 S320 / Step 2a S325, the gNB completes the RRC setup procedure. At Step 3 S330, the first Non-Access Stratum (NAS) message from the UE, piggybacked in RRCSetupComplete, is sent to the AMF. At Step 4 S340 / Step 4a S345 / Step 5 S350 / Step 5a S355, additional NAS messages may be exchanged between the UE and AMF. At Step 6 S360, the AMF prepares the UE context data (e.g., including PDU session context,the Security Key, UE Radio Capability, UE Security Capabilities, etc.) and sends the UE context data to the gNB. At Step 7 S370 / Step 7a S375, the gNB activates the AS security with the UE. At Step 8 S380 / Step 8a S385, the gNB performs the reconfiguration to setup Signalling Radio Bearer 2 (SRB2) and Data Radio Bearers (DRBs) for the UE, or SRB2 and optionally DRBs for an Integrated Access and Backhaul-Mobile Terminal (IAB-MT). At Step 9 S390, the gNB informs the AMF that the setup procedure is completed. It should be noted that the RRC messages in Steps 1 S310 and 2 S320 use SRBO, while all the subsequent messages use SRB1. The messages in Steps 7 S370 / 7a S375 are integrity protected. From Step 8 S380 on, each of the messages are integrity protected and ciphered.

[0033] There currently exist certain challenges. The problems addressed by the current disclosure are related to the security requirements associated to configuring a UE with an AI / ML functionality and the security requirements related to when the UE is allowed to start transmitting information generated based on the AI / ML configurations e.g., one or more predictions / inferences, and / or what the UE shall do when it receives an AI / ML configuration not fulfilling security requirements, when such security requirements are expected.

[0034] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. The present disclosure includes methods and systems, e.g., at the UE in which the UE receives an RRC message including an AI / ML configuration before AS security is activated e.g., during an IDLE to CONNECTED transition. In other words, the RRC message including the AI / ML configuration does not need to be encrypted or does not need to be integrity protected.

[0035] At the network side, a Radio Access Network (RAN) node (e.g., a gNodeB or a 6G RAN node), in one method transmits to a UE an RRC message including an AI / ML configuration before the AS security is activated at the UE, e.g., during an IDLE to CONNECTED transition. In other words, the RRC message including the AI / ML configuration does not need to be encrypted or does not need to be integrity protected.

[0036] The disclosure covers additional methods and systems at the UE in which the UE expects to receive an RRC message including an AI / ML configuration which is integrity protected and / or ciphered (encrypted). And, when the RRC message including the AI / ML configuration is not integrity protected and / or is not ciphered (encrypted), the UE triggers a recovery action, e.g., RRC re-establishment or NAS recovery.

[0037] At the network side a RAN node transmits an RRC message including an AI / ML configuration which is integrity protected and / or ciphered (encrypted) e.g., after the AS security is activated at the UE.

[0038] Several example embodiments and variations are given below.(2.1) Example Al

[0039] Example Al comprises a method performed by the UE, comprising: receiving an AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) before AS security is activated.

[0040] Variation A2. A method of Al, wherein the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) is received in an RRC message which is not secure.

[0041] Variation A3. A method of Al and / or A2, wherein the UE receives the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) after the UE transitions from an IDLE to a CONNECTED state, and before a procedure for setting up the AS Security is completed and / or initiated.

[0042] Variation A4. A method of Al, A2 and / or A3, wherein the UE receives the RRC message including the AI / ML configuration before the UE receives a message from the network (e.g., from a gNodeB or 6G RAN node) for setting up the AS security (e.g., before the UE receives a Security Mode Command message).

[0043] Variation A5. A method of Al, A2, A3 and / or A4, wherein, in response to the RRC message including the AI / ML configuration, transmitting to the network an RRC Response message (e.g., an RRC Reconfiguration Complete) to indicate that the UE has successfully applied the RRC message including the AI / ML configuration, wherein: the RRC response message (e.g., RRC Reconfiguration Complete) is transmitted before the AS security is activated or the RRC response message (e.g., RRC Reconfiguration Complete) is transmitted after the AS security is activated.

[0044] Variation A6. A method of Al, A2, A3, A4 and / or A5, wherein, in response to the RRC message including the AI / ML configuration, the UE transmits to the network an RRC Response message which includes an applicability indication for the AI / ML functionality.

[0045] Variation A7. A method of Al, A2, A3, A4, A5 and / or A6, wherein the RRC response message including the applicability indication for the AI / ML functionality is transmitted before the AS security is activated or after the AS security is activated.

[0046] Variation A8. A method of Al, A2, A3, A4, A5, A6 and / or A7, wherein, in response to the RRC message including the AI / ML configuration received before security is activated, transmitting to the network an applicability indication for the AI / ML functionality only after security is activated, wherein the UE transmits the applicability indication for theAI / ML functionality based on the AI / ML configuration including an applicability reporting configuration, or an inference configuration.

[0047] Variation A9. A method of Al, A2, A3, A4, A5, A6, A7 and / or A8, wherein, in response to the RRC message including the AI / ML configuration including an inference configuration, received before the AS security is activated, generating one or more inferences (e.g., predictions) as outputs of an AI / ML model and performing at least one action based on the generated inferences after the AS security is activated.

[0048] Variation A10. A method of A9, wherein the one or more actions comprise at least one of:• Performing one or more predictions of RRM measurements for a serving cell and / or for a neighbor cell and / or for a candidate cell and reporting the one or more predictions of RRM measurements to the network in an RRC report message, wherein the RRC Report message is transmitted by the UE only after AS security is activated;• Performing one or more predictions of measurement events for a serving cell and / or for a neighbor cell and / or for a candidate cell, and reporting the one or more predictions of RRM measurements to the network in an RRC report message, wherein the RRC Report message is transmitted by the UE only after AS security is activated;• Performing one or more predictions of RLF and / or handover failure (HOF) for a serving cell and / or for a neighbor cell and / or for a candidate cell and reporting the one or more predictions in an RRC report message, wherein the RRC Report message is transmitted by the UE only after AS security is activated;• Performing one or more predictions of beam measurement-related information of a serving cell and / or for a neighbor cell and / or for a candidate cell and transmitting the prediction(s) of beam measurement information to the network only after AS security is activated.

[0049] Variation Al l. The method of Al and / or all other variations, wherein the AI / ML inference configuration is a configuration for the UE to perform AI / ML inference according to one or more AI / ML models / functionalities, a configuration for the UE to perform data collection for UE-side model training of one or more AI / ML models / functionalities, or a configuration for the UE to evaluate and report the applicability of one or more AI / ML models / functionalities .(2.2) Example Bl

[0050] Example Bl comprises a method performed by a UE, comprising: receiving an AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) after AS security is activated.

[0051] Variation B2. A method of Bl, wherein the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) is received in an RRC message.

[0052] Variation B3. A method of Bl, wherein an RRC message including the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) is expected to be encrypted and / or is expected to be integrity protected based on security keys derived during an AS security activation procedure.

[0053] Variation B4. A method of B 1 and / or other variations, wherein receiving the RRC message including the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) occurs after the UE transitions from an IDLE state to a CONNECTED state, and after the procedure for setting up the AS Security is completed and / or initiated.

[0054] Variation B5. A method of Bl and / or other variations, wherein receiving the RRC message including the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) also includes DRB configuration(s).

[0055] Variation B6. A method of Bl and / or other variations, wherein the RRC message is required to be ciphered (encrypted) and / or integrity protected.

[0056] Variation B7. A method of B 1 and / or other variations, further comprising receiving an RRC message including the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) before AS security is activated and in response triggering a recovery action.

[0057] Variation B8. A method of B7, wherein the recovery action comprises one or more of: indicating a failure to the higher layers; triggering an NAS recovery procedure.

[0058] Variation B9. A method of B 1 and / or other variations, further comprising receiving an RRC message including the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) after AS security is activated and, in response to the RRC message not being secured, triggering a recovery action.

[0059] Variation B10. A method of B9, wherein the recovery action comprises an RRC re-establishment procedure or an RRC resume procedure.

[0060] Variation B 11. A method of B 1 and / or other variations, wherein upon triggering a recovery action logging information about the failure.

[0061] Variation B12. A method of Bl l, further comprising reporting information about the failure.(2.3) Example Cl

[0062] Example Cl comprises a method performed by a network node, comprising: transmitting an AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) before AS security is activated at a UE.

[0063] Variation C2. A method of Cl, wherein the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) is transmitted in an RRC message which is not secure.

[0064] Variation C3. A method of Cl and / or C2, wherein transmitting the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) occurs after the RAN node transitions the UE from an IDLE state to a CONNECTED state, and before a procedure for setting up the AS Security is completed and / or initiated.

[0065] Variation C4. A method of Cl, C2 and / or C3, wherein transmitting the RRC message including the AI / ML configuration occurs before the RAN node transmits a message from the network (e.g., from a gNodeB or 6G RAN node) for setting up the AS security (e.g., before the UE receives a Security Mode Command message).

[0066] Variation C5. A method of Cl, C2, C3 and / or C4, wherein in response to transmitting the RRC message including the AI / ML configuration, receiving, from the UE, an RRC Response message (e.g., an RRC Reconfiguration Complete) to indicate that the UE has successfully applied the RRC message including the AI / ML configuration, wherein: the RRC response message (e.g., RRC Reconfiguration Complete) is received before the AS security is activated or the RRC response message (e.g., RRC Reconfiguration Complete) is received after the AS security is activated.

[0067] Variation C6. A method of Cl, C2, C3, C4 and / or C5, wherein, in response to transmitting the RRC message including the AI / ML configuration, receiving an RRC Response message which includes an applicability indication for the AI / ML functionality.

[0068] Variation C7. A method of Cl and / or other variations, wherein the RRC response message including the applicability indication for the AI / ML functionality is received before the AS security is activated or after the AS security is activated.

[0069] Variation C8. A method of Cl and / or other variations, wherein, in response to transmitting the RRC message including the AI / ML configuration before security is activated, receiving an applicability indication for the AI / ML functionality after security is activated.

[0070] Variation C9. A method of Cl and / or other variations, wherein, in response to transmitting the RRC message including the AI / ML configuration including an inference configuration before the AS security is activated, receiving a report message from the UE including at least one report derived from an inference performed by the UE based on the AI / ML configuration, wherein the report message is received after security is activated.(2.4) Example DI

[0071] Example DI comprises a method performed by a RAN node, comprising: transmitting an AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) after AS security is activated.

[0072] Variation D2. A method of DI, wherein the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) is transmitted in an RRC message.

[0073] Variation D3. A method of DI, wherein an RRC message including the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) is expected to be encrypted and / or is expected to be integrity protected based on security keys derived during an AS security activation procedure.

[0074] Variation D4. A method of DI and / or other variations, wherein transmitting the RRC message including the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) occurs after the RAN node transitions the UE from an IDLE state to a CONNECTED state, and after the procedure for setting up the AS Security is completed and / or initiated.

[0075] Variation D5. A method of DI and / or other variations, wherein transmitting the RRC message including the AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) also includes the data radio bearers (DRBs) configuration(s).

[0076] Variation D6. A method of DI and / or other variations, wherein the RRC message is ciphered (encrypted) and / or integrity protected.

[0077] Variation D7. A method of DI, further comprising receiving information about a failure when the UE receives an RRC message including an AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) which is not secure.

[0078] Certain embodiments may provide one or more of the following technical advantages. For the case in which the UE receives an AI / ML configuration before security is activated, the UE would be able to transition from an IDLE state to a CONNECTED state and as soon as possible start to perform one or more actions based on the AI / ML configuration, such as determining an applicability indication of the AI / ML functionality (e.g., in case anapplicability reporting is configured) to be transmitted to the network, assuming the configuration is not sensitive to security attacks (even though the information that may be reported by the UE could be). The teachings of certain embodiments may improve the data rate, latency, or power consumption.

[0079] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0080] In the context of the present disclosure, the term “AI / ML functionality” may be called a “supported functionality” the UE can indicate by using UE capability signaling. A supported functionality is one or more functionalities for and / or associated with beam management and / or CSI reporting, or mobility operations, such as the reporting of time domain and / or spatial domain or frequency domain predictions (inference), Radio Link Failure (RLF) related prediction(s) and / or Handover Failure (HOF) related prediction(s), or traffic related prediction(s) e.g., of Uplink (UL) and / or Downlink (DL) incoming data. It could be said as the ability the UE has to produce an output of an inference function. For example, reporting of time-domain prediction(s) of Synchronization Signal Block (SSB) and / or (Channel State Information Reference Signal (CSI-RS) measurement information (e.g., predicted Reference Signal Received Power (RSRP)) may be considered as an AI / ML functionality which is a “supported functionality” by the UE when the UE reports a capability associated with it (via RRC or LPP signaling). Examples of potential supported functionalities are given below.

[0081] For example, “spatial domain prediction for beam management or mobility procedure, e.g., handover or reconfiguration with sync, or Primary cell (PCell) change, or Primary Secondary Cell Group cell (PSCell) change” or a related functionality (e.g., reporting and inference of spatial domain info) may be a supported functionality in which the UE may report that it is capable of performing and reporting inference / prediction of a set A of beams or cells (e.g., predicted LI RSRP values of one or more beams or one or more SSB indexes of a cell or predicted LI or L3 RSRP values of one or more cells) based on measurements performed on a set B of beams (e.g., measured L1 / L3 RSRP values of one or more beams or one or more SSB indexes of a cell), in the case of spatial domain predictions.

[0082] For example, “frequency domain prediction for beam management or mobility procedure e.g., handover” or a related functionality (e.g., reporting and inference of frequency domain info) may be a supported functionality in which the UE may indicate that is capable of performing and reporting inference, e.g., prediction of the radio link quality of a set A of beams or cells (e.g., predicted LI RSRP values of one or more beams or one or more SSB indexes ofa cell or predicted LI or L3 RSRP values of one or more cells) based on measurements performed on a set B of beams (e.g., measured L1 / L3 RSRP values of one or more beams or one or more SSB indexes of a cell or one or more cells), in the case of frequency domain predictions.

[0083] For example, “time domain prediction for beam management or a mobility procedure e.g., handover or reconfiguration with sync, or Primary cell (PCell) change, or Primary Secondary Cell Group cell (PSCell) change” or a related functionality (e.g., reporting and inference of time domain info) may be a supported functionality in which the UE may report that is capable of performing and reporting inference of a set of A of beams (e.g., predicted L1 / L3 RSRP values of one or more beams or one or more SSB indexes of a cell in future time instances or the L1 / L3 RSRP value of one or more cells in the future time instances) based on measurements performed on a set B of beams or cells (e.g., measured L1 / L3 RSRP values of one or more beams or one or more SSB indexes of a cell and / or L1 / L3 RSRP value of one or more cells), in the case of time domain predictions.

[0084] For example, beam management - downlink (DL) Transmitted (Tx) beam prediction for both UE-sided model and NW-sided model, may include: Spatial-domain DL Tx beam prediction for a Set A of beams based on measurement results of a Set B of beams (“BM- Casel”); Temporal DL Tx beam prediction for a Set A of beams based on the historic measurement results of a Set B of beams (“BM-Case2”).

[0085] For example, positioning accuracy enhancements, may include:• Direct AI / ML positioning, such as: UE-based positioning with UE-side model, direct AI / ML positioning; UE-assisted / Location Management Function (LMF) -based positioning with LMF-side model, direct AI / ML positioning; Next- Generation Radio Access Network (NG-RAN) node assisted positioning with LMF-side model, or direct AI / ML positioning.• AI / ML assisted positioning, such as: UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning; NG-RAN node assisted positioning with gNB-side model, or AI / ML assisted positioning.

[0086] For example, CSI compression, may include, e.g., extending the spatial / frequency compression to spatial / temporal / frequency compression, cell / site specific models, or CSI compression plus prediction (compared to Rel-18 non- AI / ML based approach).

[0087] For example, “Radio Link Failure prediction of serving and / or neighbor cells” or a related functionality (e.g., reporting and inference of RLF prediction of serving and / orneighbor cell(s)) may be a supported functionality in which the UE may report that is capable of performing and reporting inference of an RLF in future time instances.

[0088] For example, “Handover Failure (HOF) prediction of a cell” or a related functionality (e.g., reporting and inference of HOF prediction of a cell) may be a supported functionality in which the UE may report that it is capable of performing and reporting inference of an HOF in future time instances.(3) AI / ME Functionality Configuration (aka “AI / ML Configuration”)

[0089] In the context of the current disclosure the UE receives an AI / ME configuration (received in the cell the UE tries to connect), wherein the AI / ML configuration may include one or more parameters, IE(s), fields and / or configuration(s) necessary and / or sufficient for the UE to operate the AI / ML functionality, e.g., in the cell the UE is trying to connect. In that sense, the AI / ML configuration may include an inference configuration or an inference -related configuration (which may also be considered a full and / or complete inference configuration, sufficient for the operation of the AI / ML functionality). In other words, when the UE receives in a CONNECTED state the inference configuration or an inference related configuration for an AI / ML functionality, then the UE can generate inference information (e.g., as output of an AI / ML model associated with the AI / ML functionality) and possibly report the inference information to the network.

[0090] In the context of the present disclosure, an inference configuration or an inference related configuration may correspond to a Channel State information (CSI) measurement configuration (e.g., in an IE CSI-MeasConfig, CSI-ReportConfig, CSI-ResourceConfig) associated with a set A and or set B of beams for a beam management AI / ML functionality. The inference configuration may further include one or more of: Synchronization Signal Block (SSB) identifiers associated with a serving cell and / or a neighbor cell; CSLRS resource identifiers associated with a serving cell and / or a neighbor cell; beam identifiers associated with a serving cell and / or a neighbor cell; Mobility Reference Signal(s) identifiers associated with a serving cell and / or a neighbor cell; candidate inference configuration(s) Set A and / or B (1); Set A and / or B (2); Set A and / or B (3), etc.

[0091] In the context of the present disclosure, an inference configuration or an inference related configuration may correspond to a mobility prediction configuration or Radio resource management (RRM) measurement configuration associated with a mobility procedure to run the inference and report the predictions. The RRM measurement configurations (e.g., measConfig) may include, e.g., one or more of: a list of one or more measurement objects toadd / modify / remove by the UE (which may further include, e.g., SSB frequency; CSI-RS frequency; SSB subcarrier spacing; measurement timing configuration; SSB and or CSI-RS beam consolidation configuration / threshold; or Number of SSB or CSI-RS measurements to average); a list of one or more report configuration to add / modify / remove by the UE; SpCell RSRP measurement controlling when the UE is required to perform measurements on nonserving cells; a measurement gap configuration e.g., a measurement gap ID, identifying the measurement gap ID per FR; or a measurement quantity configuration.

[0092] In the context of the present disclosure, an inference configuration or an inference- related configuration may include a first set (set A) of measurement resources (e.g., beams, SSB indexes and / or CSI-RS resource identifiers, Mobility Refence Signal identifiers, etc.) in which the UE performs radio measurement predictions (inferences, such as predicted RSRP values), and a second set (set B) of radio measurement resources (e.g., beams, SSB indexes and / or CSI-RS resource identifiers, Mobility Refence Signal identifiers, etc.) in which the UE can perform radio measurement in order to determine the radio measurement predictions on the first set. The inference configuration may also include one or more configuration(s) associated with network side (NW-side) additional conditions reflecting the NW operational properties, such as: Set A and / or Set B of resources, represented, e.g., by: an ID associated to the set of resources or to the resources within the set; a mapping relationship between Set A and Set B, including ordering to a set of IDs or resources; consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B; a Quasi-Co- Location (QCL) assumption; the order of model input and model output between RS and Tx beams can be pre-defined; gNB transmission power; UE distribution; gNB antenna height and / or other antenna properties; Network deployment scenarios (e.g., ISD, Umi / Uma); NW- side resource configuration(s) which may be considered as NW implementation-based configurations which may possibly impact the inference performance for a UE sided model, for instance, a beam and Tx port mapping relationship in the gNodeB for a given cell, NW antenna shape, antenna dip angle, height of the tower / gNB, etc.; NW load in terms of connected users, or radio resource utilizations (e.g., Physical Downlink Control Channel (PDCCH) / Random Access Channel (RACH) / Physical Uplink Control Channel (PUCCH) / Physical Uplink Shared Channel (PUSCH) / Physical Downlink Shared Channel (PDSCH) resource load, number of configured bearers, etc.).

[0093] The inference configuration or an inference -related configuration which the UE has received may include a list of IDs referring to the set A and set B (or to the resources within the set A / B) and referring to one or more NW-side additional conditions.

[0094] In the context of the present disclosure, the AI / ML functionality configuration may include one or more of the following:• An inference configuration for a beam management functionality (e.g., timedomain prediction of beam information). In one example, the inference configuration includes a reporting configuration including parameters indicating how the UE is to report time-domain predictions of beam information (e.g., beam indexes and / or SSB indexes and / or time-domain prediction of beam measurements) and / or spatial-domain predictions of beam information. In one example, the inference configuration includes the resource configuration for resources (e.g., SSB indexes and / or CSI-RS resources) which the UE measures and provides as input to an AI / ML model (or inference function) to produce inference outputs e.g., the actual time-domain predictions of beam information (e.g., beam indexes and / or SSB indexes and / or time-domain prediction of beam measurements) and / or spatial-domain predictions of beam information to be included in a report.• An inference configuration for a L3 Mobility functionality. In one example, the inference configuration includes the reporting configuration including parameters indicating how the UE is to report time-domain predictions for neighbor cell(s) which are candidates for a connected mode inter-cell mobility procedure, or for serving cells. The time-domain predictions may be cell identifiers, time-domain predictions of measurements, such as predicted Reference Signal Received Power (RSRP), predicted Reference Signal Received Quality (RSRQ), as predicted Signal to Interference plus Noise Ratio (SINR) and / or spatial-domain predictions of cell(s). In one example, the inference configuration includes a configuration for the UE to predict the occurrence of RLF in the second cell. In one example, the inference configuration includes the configuration for the UE to predict the future occurrence of HOF when the UE is in second cell and later would move to yet another cell. In one example, the inference configuration includes the configuration for the UE to predict the future occurrence of the fulfillment of a measurement reporting event such as an event Al, A2, A3, A4, A5, A6, Bl, B2, etc.An inference configuration for positioning functionality;• An inference configuration for CSI reporting functionality;• A configurating enabling the UE to determine whether the AI / ML functionality is applicable or not. In one option the UE has reported whether the AI / ML functionality of the second cell (which is the target cell) was applicable or not. However, as that may have changed from the time the UE has transmitted the report (until the time in which the UE is to access the second cell in the handover);• Network conditions such as Set A / set B configuration(s);• A state indication for the AI / ML functionality, e.g., ‘activated’, ‘inactivated’, ‘deactivated’ ;• An indication on whether the UE is allowed to consider the AI / ML functionality as ‘activated’ when the functionality is determined by the UE to be applicable.

[0095] The AI / ML configuration may include also an identifier of the AI / ML functionality to which the configuration (e.g., inference configuration) is referred to, wherein the AI / ML functionality could be for example, beam management functionality, spatial beam management functionality, temporal beam management functionality, L3 mobility functionality, positioning functionality, CSI compression functionality, CSI prediction functionality, etc.

[0096] In the context of the present disclosure, the UE receives an AI / ML configuration (received in the cell the UE tries to connect to), wherein the AI / ML configuration may include one or more parameters, IE(s), fields and / or configuration(s) necessary and / or sufficient for the UE to perform data collection for training an AI / ML model associated to an AI / ML functionality.

[0097] In the context of the present disclosure; the UE receives an AI / ML configuration (received in the cell the UE tries to connect), wherein the AI / ML configuration may include one or more parameters, IE(s), fields and / or configuration(s) necessary and / or sufficient for the UE to perform the monitoring of the performance of an AI / ML model and / or AI / ML functionality.

[0098] In the context of the present disclosure, an AI / ML configuration may include one or more parameters, IE(s), fields and / or configuration(s) necessary and / or sufficient for the UE to evaluate and report the applicability of the AI / ML functionality which could be called an applicability reporting configuration. In other words, when the UE receives the applicability reporting configuration for an AI / ML functionality the UE determines whether the AI / ML functionality supported by the UE, and / or the associated configuration(s) of that AI / MLfunctionality, is applicable or not applicable. The applicability reporting configuration may include one or more of the following:• An indication that the UE is allowed to do UE assistance information reporting, e.g., by configuring UE assistance information reporting in the IE OtherConfig of the RRCReconfiguration message.• An indication of the AI / ML functionality for which the UE should transmit the applicability reporting, e.g., indications of the applicability associated the indicated AI / ML functionality.• One or more NW-side additional condition(s) (included, e.g., in the IE OtherConfig in the RRCReconfiguration message, e.g., for the UE to determine whether the AI / ML model / functionality has been trained under similar conditions, such as one or more of the following: a. Configuration(s) related to the mapping relationship of Set A and Set B, including ordering to a set of IDs, or resources. b. Configuration(s) related to the consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B. In that context, consistency may correspond to one or more of: Set size consistency for Set B, Set A: consistency in number of beams and / or associated resources for Set B and Set A, across training and inference; periodicity consistency for Set B, Set A: consistency in periodicity of beams and / or associated resources for Set B and Set A, across training and inference; relationship of Set A / Set B (Set B is a subset of Set A or not): consistency in relationship of beams and / or associated resources for Set B and Set A, i.e., whether Set B is a subset of Set A, across training and inference. c. Configuration(s) related to the Quasi-Co-Location (QCL) assumption(s). d. Beam configuration(s) of the network such as: Beam characteristics, e.g., beam boresight direction (azimuth and elevation), 3dB beamwidth. In one sub-option the beam characteristics may be associated to an identifier indicated to the UE during training and AI / ML configuration, for checking of the consistency between training and inference; Set A / Set B related info, e.g., the beam index of set B; Information aboutthe beam codebook and / or indexing / mapping of Set A and Set B, e.g., info on whether the AI / ML Model / functionality is trained with a data set with a certain beam codebook and index / mapping of Set A / Set B, inference works for the same beam codebook and index / mapping of Set A / Set B. e. Configuration(s) related to the order of model input and model output between RS and Tx beams can be pre-defined. f. Configuration(s) related to the transmission power and / or power levels the gNodeB and / or the serving cells are operating. g. Configuration(s) related to the UE distribution. h. Configuration(s) related to Antenna height. i. Configuration(s) related to the deployment scenarios (e.g., Inter-Site Distance (ISD), Urban Microcellular (Umi) / Urban Macrocellular (Uma) / rural / indoor / indoor office / indoor factory specific area(s)). j. Configuration(s) related to UE speed• An indication of an identifier (associated ID) associated to one or more network conditions, so that the UE assumes that NW-side additional conditions with the same associated ID are consistent at least within a cell.• In one option, NW-side additional condition may be associated with an inference configuration (e.g., resource set A, to be inferred and / or estimated and / or predicted, and / or resource set B, in which the UE should perform the measurement to infer / estimate / predict the radio measurement associated with the set A resources) and / or one training configuration (e.g., resource of CSI resources configured by the gNB at the time of the UE performing UE-side model training) identified by the same associated ID, for the second cell (which is a neighbor cell which may become the target cell in a handover). The UE may perform training of one or AI / ML functionalities / models with different sets of collected data via training configuration identified by its associated ID (e.g., one associated ID->one training configuration->one Al model).• An inference configuration.(4)Indication for an AI / ML Functionality

[0099] In the context of the present disclosure, the applicability indication of an AI / ML functionality, which may be transmitted by the UE in an RRC Response message (e.g., an RRC Reconfiguration Complete and / or a UE Assistance Information), e.g., after security is activated, may comprise one or more of the following:• An indication indicating that the AI / ML functionality is ‘applicable’. In one option, this indication corresponds to a field and / or IE and / or parameter.• An indication indicating that the AI / ML functionality is ‘not applicable’ (or ‘non-applicable’). In one option, this indication corresponds to a field and / or IE and / or parameter. In one option, this indication corresponds to the absence of a field and / or the absence of an IE and / or the absence of a parameter.• An indication of an applicability status, which may take one or more values, such as ‘applicable’ or ‘not applicable’.• A recommended (or preferred) AI / ML functionality configuration for which the AI / ML functionality becomes applicable, e.g., the indication indicates that the AI / ML functionality may not be applicable for a configuration (x), but it may be applicable for a configuration (y), wherein the applicability indication corresponds to an indication of configuration (y).• An identifier associated with one or more NW-side additional conditions associated with the AI / ML model, e.g., the identifier of the NW configuration(s) (settings) in which the AI / ML model was trained.

[0100] In the context of the present disclosure, upon receiving the AI / ML configuration in the RRC message (e.g., RRCReconfiguration) the UE determines the applicability indication for the AI / ML functionality, to be included in the RRC Response message (e.g., an RRC Reconfiguration Complete and / or a UE Assistance Information), based on one or more UE conditions and / or one or more network conditions and / or based on an inference configuration. Hence, prior to transmitting the applicability indication (e.g., before AS security activation), the UE evaluates the applicability of the AI / ML model / functionality and takes into account the NW-side additional conditions, and UE-side additional conditions, wherein the latter could be represented by, e.g., UE speed; UE battery status; UE antenna properties (layout, MIMO configuration, device orientation etc.); UE radio configuration; or UE traffic type.

[0101] In the context of the current disclosure, an AI / ML configuration may be a configuration for the UE to perform data collection for the UE-side model training, and it can comprise one or more configuration(s) associated with network side (NW-side) additionalconditions reflecting the NW operational properties, and measurement configuration for the UE to collect data measurements, for example based on set A / B configuration, and optionally also a reporting configuration for the UE to report the collected data measurements to the gNB.

[0102] In the context of the present disclosure, the UE may receive an AI / ML configuration before the AS security is activated, e.g., during an IDLE state to CONNECTED state transition. In this context, the AS security would be considered activated when the UE receives a message for AS security activation (e.g., Security Mode Command), including one or more security related parameters (e.g., algorithm configuration, one or more counters, etc.) and, in response to that, when the UE performs one or more of the following steps:• deriving a key related to a RAN network node (e.g., KgNB key or a K6GRANnode key), such as a gNodeB or a 6G RAN network node;• deriving an integrity protection key for control plane message (e.g., KRRCint key); that may be associated to an integrity protection algorithm (e.g., configured in the Security Mode Command, like integrity Prot Algorithm);• requesting lower layers to verify the integrity protection of the message for activating the AS security (e.g., SecurityModeCommand message), using the algorithm indicated by the message and the integrity protection key for control plane message (e.g., KRRCint key);• performing one or more further actions when the message for AS security activation (e.g., the SecurityModeCommand message) passes the integrity protection check, such as: deriving a ciphering (encryption) key for control plane message (e.g., KRRCenc key) and ciphering (encryption) key for user plane data (e.g., KUPenc key), associated with a ciphering (encryption) algorithm e.g., cipheringAlgorithm indicated in the SecurityModeCommand message; deriving an integrity protection key for user plane data (e.g., KUPint key) associated with an integrity protection algorithm e.g., the integrityProtAlgorithm indicated in the SecurityModeCommand message; configuring lower layers to apply SRB integrity protection using the indicated algorithm and the integrity protection key for control plane message (e.g., KRRCint key) immediately, e.g., integrity protection shall be applied to all subsequent messages received and sent by the UE, including the message indicating that the AS security is activated (e.g., the Security ModeComplete message); configuring lower layers to apply SRB ciphering (encryption) usingthe indicated algorithm and the ciphering (encryption) key for control plane message (e.g., KRRCenc key) after completing the procedure, e.g., ciphering (encryption) shall be applied to all subsequent messages received and sent by the UE, except for the message indicating that the AS security is activated (e.g., the SecurityModeComplete message), which is sent unciphered; consider AS security to be activated; submit the message indicating that the AS security is activated (e.g., the SecurityModeComplete message) to lower layers for transmission.(5) AI / ML Configuration Expected to be Received Before Security is Activated

[0103] In one set of embodiments, the UE receives an AI / ML configuration (e.g., a configuration associated with an AI / ML functionality) before security is activated (e.g., before the Access Stratum (AS) Security is activated). In other words, the UE receives the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) in an RRC message which is not secure e.g., an RRC message which is not encrypted, and / or an RRC message which is not integrity protected.

[0104] In one option, the UE is in an IDLE state (e.g., RRC_IDLE) and determines to transition to a CONNECTED state (e.g., RRC_CONNECTED). While in RRC_IDLE, the AS security at the UE is deactivated. In response to determining to transition to the CONNECTED state, the UE transmits a request to setup the connection (e.g., RRC Setup Request), receives a message for setting up the connection, such as an RRC Setup message (e.g., for configuring a Signaling Radio Bearer e.g., SRB1), in response to which the UE enters the CONNECTED state; then, the UE transmits a message to complete the setup procedure, such as an RRC setup complete message. At that point, the UE has an SRB which is setup (e.g., SRB1); then, before the UE finalizes the setup of the AS security (e.g., before AS security is activated), the UE receives from the network (e.g., from a gNodeB or 6G RAN node the UE is trying to connect to) an RRC message (e.g., RRC Reconfiguration) including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality).

[0105] Figure 4 illustrates an example 400 of an IDLE state to CONNECTED state transition in which a UE receives an RRC Reconfiguration including an AI / ML configuration before the UE receives a Security Mode Command, in accordance with some embodiments. An interaction between a UE (e.g., UE 402), a gNB (e.g., gNB 404), and an AMF, (e.g., AMF 406) is shown. As in Figure 3 above, the initial steps of Figure 4 are as follows. At Step 1 S410, the UE (e.g., UE 402) sends, to the network (e.g., gNB 404), a request to setup a newconnection from RRC_IDLE. At Step 2 S420 / Step 2a S425, the gNB completes the RRC setup procedure. At Step 3 S430, the first NAS message from the UE, piggybacked in RRCSetupComplete, is sent to the AMF. At Step 4 S440 / Step 4a S445 / Step 5 S450 / Step 5a S455, additional NAS messages may be exchanged between the UE and AMF. At Step 6 S460, the AMF prepares the UE context data (e.g., including PDU session context, the Security Key, UE Radio Capability and UE Security Capabilities, etc.) and sends the UE context data to the gNB.

[0106] In an embodiment, there may be different options concerning the timing in which the UE receives the RRC message including the AI / ML configuration.

[0107] In one option, the UE receives the RRC message (e.g., RRC Reconfiguration) including the AI / ML configuration before the UE receives a message from the network (e.g., from a gNodeB or 6G RAN node) for setting up the AS security (e.g., before the UE receives a Security Mode Command message). An example is shown in Figure 4: the UE transitions from RRC_IDLE to RRC_CONNECTED and receives in Step 7 S470 an RRC Reconfiguration including an AI / ML configuration, before it receives the Security ModeCommand e.g., before it can activate the AS security. The UE sends, to the network, an RRC reconfiguration complete message at Step 7a S475. Notice that the gNB sends the RRC Reconfiguration including an AI / ML configuration after it receives from the AMF, in Step 6 S460, the INITIAL UE CONTEXT SETUP, which includes the UE capabilities indicating that the UE is capable of the AI / ML functionality associated with the AI / ML configuration provided to the UE in Step 7 S470.

[0108] In one option, the UE receives the RRC message (e.g., RRC Reconfiguration) including the AI / ML configuration before the UE transmits a message to the network (e.g., to the gNodeB or to the 6G RAN node) which indicates to the network that it has activated the AS security (e.g., before the UE transmits a Security Mode Complete message). In other words, the UE may receive the RRC message including the AI / ML configuration after the message from the network (e.g., from a gNodeB or 6G RAN node) for setting up the AS security (e.g., before the UE receives a Security Mode Command message) or multiplexed with it, e.g., in the same Medium Access Control (MAC) Protocol Data Unit (PDU). But the UE may still process the RRC message including the AI / ML configuration before AS security is actually activated, so that the UE may process the RRC message before sending the Security Mode Complete message at Step 8a S485. At Step 9 S490 / Step 9a S495, the gNB performs the reconfiguration to setup SRB2 and DRBs for the UE, or SRB2 and optionally DRBs for IAB-MT. At Step 10 S498, the gNB informs the AMF that the setup procedure is completed.

[0109] There may be different options concerning the transmission by the UE of an RRC response message (e.g., its transmission timing and its content), after the UE receives the RRC message including AI / ML configuration.

[0110] Figure 5 illustrates an example 500 of an IDLE to CONNECTED transition in which a UE transmits an RRC Response message including an applicability indication for an AI / ML functionality before it receives a Security Mode Command, in accordance with some embodiments. An interaction between a UE (e.g., UE 502), a gNB (e.g., gNB 504), and an AMF, (e.g., AMF 506) is shown. As in Figures 3 and 4 above, the initial steps of Figure 5 are as follows. At Step 1 S510, the UE (e.g., UE 502) sends, to the network (e.g., gNB 504), a request to setup a new connection from RRC_IDLE. At Step 2 S520 / Step 2a S525, the gNB completes the RRC setup procedure. At Step 3 S530, the first NAS message from the UE, piggybacked in RRCSetupComplete, is sent to the AMF. At Step 4 S540 / Step 4a S545 / Step 5 S550 / Step 5a S555, additional NAS messages may be exchanged between the UE and AMF. At Step 6 S560, the AMF prepares the UE context data (e.g., including PDU session context, the Security Key, UE Radio Capability and UE Security Capabilities, etc.) and sends the UE context data to the gNB.

[0111] In an embodiment, Figure 5 shows an example of an IDLE state to CONNECTED state transition in which the UE transmits the RRC Response message (e.g., RRC Reconfiguration Complete) including the applicability indication for the AI / ML functionality at Step 7a S575, before it receives the Security Mode Command at Step 8 S580. The UE may process the RRC message before sending the Security Mode Complete message at Step 8a S585. At Step 9 S590 / Step 9a S595, the gNB performs the reconfiguration to setup SRB2 and DRBs for the UE, or SRB2 and optionally DRBs for IAB-MT. At Step 10 S598, the gNB informs the AMF that the setup procedure is completed.

[0112] Figure 6 illustrates an example 600 of an IDLE state to CONNECTED state transition in which a UE transmits an RRC Reconfiguration Complete before security activation and a UAI message (RRC response) including an applicability indication for an AI / ML functionality after security is activated, in accordance with some embodiments. An interaction between a UE (e.g., UE 602), a gNB (e.g., gNB 604), and an AMF, (e.g., AMF 606) is shown. As in Figures 3-5 above, the initial steps of Figure 6 are as follows. At Step 1 S610, the UE (e.g., UE 602) sends, to the network (e.g., gNB 604), a request to setup a new connection from RRC_IDLE. At Step 2 S620 / Step 2a S625, the gNB completes the RRC setup procedure. At Step 3 S630, the first NAS message from the UE, piggybacked in RRCSetupComplete, is sent to the AMF. At Step 4 S640 / Step 4a S645 / Step 5 S650 / Step 5a S655, additional NASmessages may be exchanged between the UE and AMF. At Step 6 S660, the AMF prepares the UE context data (e.g., including PDU session context, the Security Key, UE Radio Capability and UE Security Capabilities, etc.) and sends the UE context data to the gNB.

[0113] In an embodiment, Figure 6 shows an example of an IDLE state to CONNECTED state transition in which the UE transmits an RRC Reconfiguration Complete at Step 7a S672 before security activation at Step 8 S680 / Step 8a S685 and the UAI message (RRC response) at Step 7b S 674 including the applicability indication for the AI / ML functionality after security is activated. At Step 9 S690 / Step 9a S695, the gNB performs the reconfiguration to setup SRB2 and DRBs for the UE, or SRB2 and optionally DRBs for IAB-MT. At Step 10 S698, the gNB informs the AMF that the setup procedure is completed.

[0114] In one option, in response to the RRC message including the AI / ML configuration the UE transmits to the network (e.g., to the gNodeB or to the 6G RAN node) an RRC Response message (e.g., an RRC Reconfiguration Complete). That RRC Response message (e.g., an RRC Reconfiguration Complete) may be transmitted to indicate that the UE has successfully applied the RRC message including the including the AI / ML configuration. In one sub-option, the UE transmits the RRC response message (e.g., RRC Reconfiguration Complete) before the AS security is activated. In other words, the UE processes the RRC message with the AI / ML configuration, generates RRC Response message and transmits the RRC Response message before the UE activates the AS security to as soon as possible acknowledge to the network that the UE has received and properly processed the RRC message including the AI / ML configuration. This is shown in Figure 4 as described above. In a sub-option the UE transmits the RRC response message (e.g., RRC Reconfiguration Complete) after the AS security is activated at Step 7a S475. Thus, the UE processes the RRC message with the AI / ML configuration before security is activated, but it only generates RRC Response message and / or transmits the RRC Response after it activates the AS security. Thus, the UE may receive the RRC message before security is activated e.g., the RRC message is not encrypted, and / or is not integrity protected; however, the RRC response may be encrypted and / or integrity protected with the AS security keys derived by the UE.

[0115] In one option, in response to the RRC message including the AI / ML configuration, the UE transmits to the network (e.g., to the gNodeB or to the 6G RAN node) an RRC Response message (e.g., an RRC Reconfiguration Complete or UE Assistance Information), which includes an applicability indication for the AI / ML functionality. In one sub-option the UE transmits the RRC response message including the applicability indication for the AI / ML functionality also before the AS security is activated so the network obtains the applicabilityindication for the AI / ML functionality as soon as possible (assuming the information is not sensitive to security attacks), so that the AI / ML functionality may be activated as soon as possible and the UE may start performing the inferences (to be later reported) as soon as possible. In other words, the UE processes the RRC message with the AI / ML configuration, determines whether the AI / ML functionality is applicable or not, generates RRC Response message including applicability indication for the AI / ML functionality and transmits the RRC Response, before the UE activates the AS security, to as soon as possible acknowledge to the network that it has received and properly processed the RRC message including the AI / ML configuration. In one sub-sub-option the RRC Response message corresponds to an RRC Reconfiguration Complete, in response to the RRC Reconfiguration including the AI / ML configuration. This is shown in Figure 5 as described above. In a sub-option the UE transmits the RRC response message after the AS security is activated when the UE needs to include an applicability indication for the AI / ML functionality. Thus, the UE processes the RRC message with the AI / ML configuration before security is activated, but only generates RRC Response message including the applicability indication for the AI / ML functionality and / or transmits the RRC Response after the UE activates the AS security. Thus, the UE may receive the RRC message before security is activated e.g., the RRC message is not encrypted, and / or is not integrity protected; however, the RRC response may be encrypted and / or integrity protected with the AS security keys derived by the UE. This prevents an attacker from sending an RRC Response message (not secured) to indicate that an AI / ML functionality is applicable when in fact it may not be (which may cause the network to configure the UE with an inference configuration which the UE does not comply with, which may trigger an RRC Reestablishment or Non-Access Stratum Recovery). An important step in this option is the UE determining whether the configuration includes an applicability reporting configuration or not. When the configuration does include an applicability reporting configuration, the UE needs to transmit the applicability indication for the AI / ML functionality and that is when the UE determines to transmit the RRC Response after security is activated, When the configuration does not include an applicability reporting configuration, the UE may transmit the RRC Response before security is activated. In one sub-sub-option, the RRC Response message corresponds to an RRC Reconfiguration Complete, in response to the RRC Reconfiguration including the AI / ML configuration. In one sub-sub-option, the RRC Response message corresponds to a UE Assistance Information (UAI) message, in response to the RRC Reconfiguration including the AI / ML configuration (e.g., including otherConfig indicating an applicability reporting configuration). In one sub-sub-option, the RRC Response messagecorresponds to a UAI message including the applicability indication for the AI / ML functionality. However, the UE transmits the RRC Reconfiguration Complete in response to the RRC Reconfiguration including the AI / ML configuration (see Step 7a S672), before security is activated, and transmits a UAI message including the applicability indication for the AI / ML functionality after security is activated (see Step 7b S674). In that case, the UAI message may be encrypted and / or integrity protected based on the AS security keys derived when security is activated (e.g., with K8NB, KRRcint, KRRCEUC). This example is shown in Figure 6 as described above.

[0116] In one option, the UE receives the RRC message on the SRB which was setup (e.g., SRB1) during the IDLE state to CONNECTED state transition (e.g., reception of the RRC Setup). In one option, the same SRB is used for the RRC Response message.

[0117] In one option, the UE receives the RRC message including the AI / ML configuration before security is activated and transmits to the network an applicability indication for the AI / ML functionality only after security is activated, e.g., in a UE Assistance Information message (or in an RRC Reconfiguration Complete). Thus, the UE transmits the applicability indication for the AI / ML functionality in an RRC message which is encrypted based on one or more AS security keys (e.g., K8NB, KRRCenc) and / or integrity protected based on one or more AS security keys (e.g., K8NB, KRRcint), e.g., after the AS security is activated. In one sub-option, the UE transmits the applicability indication for the AI / ML functionality based on the AI / ML configuration including an applicability reporting configuration, or an inference configuration. In one sub-option, the UE transmits the applicability indication for the AI / ML functionality in an RRC message transmitted after the UE has received the message configuring the AS security (e.g., Security Mode Command message). In one sub-option, the UE transmits the applicability indication for the AI / ML functionality in an RRC message transmitted after the UE has received the message for activating the AS security (e.g., Security Mode Command message) and after the UE has activated security and after the UE derives the AS security keys (e.g., K8NB, KRRcint, KRRCenc). In one sub-option, the UE transmits the applicability indication for the AI / ML functionality in an RRC message transmitted after the UE has transmitted the message to indicate that the AS security is activated (e.g., Security Mode Complete message). In one sub-option, the UE transmits the applicability indication for the AI / ML functionality in an RRC message transmitted multiplexed with the message to indicate that the AS security is activated (e.g., Security Mode Complete message).

[0118] In one option, in response to the RRC message including the AI / ML configuration including an inference configuration, received before the AS security is activated, the UEgenerates one or more inferences (e.g., predictions) as outputs of an AI / ML model however, the UE may perform at least one action based on the generated inferences after the AS security is activated. There could be actions performed by the UE before AS security is activated. For example, when the inference configuration indicates to the UE to perform predictions of Radio Resource Management (RRM) measurements (e.g., predicted RSRP values and / or predicted RSRQ values and / or predicted SINR values) for a serving cell and / or for a neighbor cell and / or for a candidate cell, and indicates that the UE shall report the predictions of RRM measurements to the network in an RRC report message (e.g., RRC Measurement Report or RRC Prediction Report), the RRC Report message including the predictions of Radio Resource Management (RRM) measurements (e.g., time domain prediction(s), spatial-domain prediction(s), frequency domain prediction(s)) is transmitted by the UE only after AS security is activated; in one sub-option the UE may start performing the inferences upon reception of the AI / ML configuration (inference configuration). Actually, one of the benefits in receiving the AI / ML configuration before AS security is to speed up the availability of the inferences; but reporting only after AS security is activated secures that the UE situation (e.g., position) will not be eavesdropped by a malicious entity, since the message including the inferences needs to be secured, e.g., encrypted and integrity protected. For example, when the inference configuration indicates to the UE to perform predictions of the triggering of a measurement event (e.g., predicted that in a future time instance an event like Al, A2, A3, A4, A5, A6, Bl, B2, Hl, H2) is going to be triggered (e.g., based on predicted RSRP values and / or predicted RSRQ values and / or predicted SINR values) for a serving cell and / or for a neighbor cell and / or for a candidate cell, and indicates that the UE shall trigger a report to the network in an RRC report message (e.g., an RRC Measurement Report or RRC Prediction Report), the RRC Report message indicating the future trigger of the event (and possibly including the predictions e.g., time domain prediction(s), spatial-domain prediction(s), frequency domain prediction(s)) is transmitted by the UE only after AS security is activated; in one sub-option the UE may start performing the inferences and / or evaluating fulfillment of trigger conditions upon reception of the AI / ML configuration (inference configuration). For example, when the inference configuration indicates to the UE to perform predictions of RLF and / or HOF for a serving cell and / or for a neighbor cell and / or for a candidate cell, and indicates that the UE shall report the RLF and / or HOF predictions to the network in an RRC report message (e.g., an RRC Measurement Report or RRC Prediction Report), the RRC Report message including the predictions of RLF and / or HOF (e.g., time domain prediction(s), spatial-domain prediction(s), frequency domain prediction(s)) is transmitted by the UE only after AS security is activated.In one sub-option, the UE may start performing the inferences of RLF and / or HOF upon reception of the AI / ME configuration (inference configuration). For example, when the inference configuration indicates to the UE to perform beam measurement related predictions, e.g., predictions of SSB(s) and / or CSI-RSs for beam(s) of a serving cell (e.g., PCell, PSCell, SCells of the MCg, SCells of the SCG) and / or for a neighbor cell and / or for a candidate cell, and indicates that the UE shall report prediction(s) of beam measurement information to the network (e.g., in a report, like in a MAC CE and / or over LI) that is transmitted by the UE only after AS security is activated.

[0119] In this set of embodiments, the UE does not expect to receive an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) after security is activated (e.g., before the Access Stratum (AS) Security is activated), which means that the UE is allowed to receive and process the RRC message including the AI / ML configuration before the AS security is activated. In other words, the UE expects to receive the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) in an RRC message which is not secure. Thus, receiving the not secure RRC message does not lead to a handling failure, e.g., the UE does not trigger a re-establishment nor a Non-Access Stratum recovery due to an RRC message which is not secure.(6) AI / ML Configuration Expected to be Received After Security is Activated

[0120] In one set of embodiments, the UE expects to receive an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) after security is activated (e.g., before the Access Stratum (AS) Security is activated). In other words, the UE expects to receive the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) in an RRC message which is secure, e.g., an RRC message which is encrypted and / or integrity protected based on security keys derived during AS security activation.

[0121] In one option, the UE is in an IDLE state (e.g., RRC_IDLE) and determines to transition to a CONNECTED state (e.g., RRC_CONNECTED). While in RRC_IDLE, the AS security at the UE is deactivated. In response to determining to transition to the CONNECTED state, the UE transmits a request to setup the connection (e.g., RRC Setup Request), receives a message for setting up the connection, such as an RRC Setup message (e.g., for configuring a Signaling Radio Bearer e.g., SRB1), in response to which the UE enters the CONNECTED state. Then, the UE transmits a message to complete the setup procedure, such as an RRC setup complete message. At that point, the UE has an SRB which is setup (e.g., SRB1); then, after the UE finalizes the setup of the AS security (e.g., after AS security is activated), the UEreceives from the network (e.g., from a gNodeB or 6G RAN node the UE is trying to connected to) an RRC message (e.g., RRC Reconfiguration) including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality).

[0122] Figure 7 illustrates an example 700 of an IDLE state to CONNECTED state transition in which a UE receives an RRC message including an AI / ML configuration after Access Stratum (AS) security activation, in accordance with some embodiments. An interaction between a UE (e.g., UE 702), a gNB (e.g., gNB 704), and an AMF, (e.g., AMF 706) is shown. Particularly, in the example IDLE state to CONNECTED state transition, the UE receives the RRC message including the AI / ML configuration after AS security activation, e.g., after the UE receives the Security Mode Command and after the UE sends the Security Mode Complete message. As in Figures 3-6 above, the initial steps of Figure 7 are as follows. At Step 1 S710, the UE (e.g., UE 702) sends, to the network (e.g., gNB 704), a request to setup a new connection from RRC_IDLE. At Step 2 S720 / Step 2a S725, the gNB completes the RRC setup procedure. At Step 3 S730, the first NAS message from the UE, piggybacked in RRCSetupComplete, is sent to the AMF. At Step 4 S740 / Step 4a S745 / Step 5 S750 / Step 5a S755, additional NAS messages may be exchanged between the UE and AMF. At Step 6 S760, the AMF prepares the UE context data (e.g., including PDU session context, the Security Key, UE Radio Capability and UE Security Capabilities, etc.) and sends the UE context data to the gNB.

[0123] In an embodiment, there may be different options concerning the timing in which the UE receives the RRC message including the AI / ML configuration after AS security is activated.

[0124] In one option, the UE receives the RRC message (e.g., RRC Reconfiguration) including the AI / ML configuration after the UE receives a message from the network (e.g., from a gNodeB or 6G RAN node) for setting up the AS security (e.g., before the UE receives a Security Mode Command message). An example is shown in Figure 7: the UE transitions from RRC_IDLE to RRC_CONNECTED and receives at Step 9 S 790 an RRC Reconfiguration including an AI / ML configuration (e.g., together with the DRB configurations), after it has received the message activating security (e.g., SecurityModeCommand) at Step 8 S780 and after it has transmitted the message to indicate the AS security activation (e.g., Security Mode Complete) at Step 8a S785. Notice that the gNB sends the RRC Reconfiguration including an AI / ML configuration at Step 9 S790 after it receives from the AMF, at Step 6 S760, the INITIAL UE CONTEXT SETUP, which includes the UE capabilities indicating that the UE iscapable of the AI / ML functionality associated to the AI / ML configuration. At Step 10 S798, the gNB informs the AMF that the setup procedure is completed.

[0125] In another example, the UE may transition from RRC_IDLE to RRC_CONNECTED and receive an RRC Reconfiguration including an AI / ML configuration (e.g., together with the Data radio bearer configurations) multiplexed with the RRC message activating security (E.g., Security ModeCommand). However, in this scenario the UE also may first process the RRC message activating security, activate AS security, and process the RRC Reconfiguration message including the AI / ML configuration.(8) UE Actions When the UE Expects a Secure RRC Message

[0126] In some embodiments, the UE expects a secure RRC message including the AI / ML configuration, but the message is not secure.

[0127] In one set of embodiments, the UE expects to receive an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) after security is activated (e.g., before the Access Stratum (AS) Security is activated). In other words, the UE expects to receive the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) in an RRC message which is secure e.g., an RRC message which is encrypted and / or integrity protected based on security keys derived during AS security activation.

[0128] In one option, the UE is in an IDLE state (e.g., RRC_IDLE) and determines to transition to a CONNECTED state (e.g., RRC_CONNECTED). While in RRC_IDLE, the AS security at the UE is deactivated. In response to determining to transition to the CONNECTED state, the UE transmits a request to setup the connection (e.g., RRC Setup Request), receives a message for setting up the connection, such as an RRC Setup message (e.g., for configuring a Signaling Radio Bearer e.g., SRB1), in response to which the UE enters the CONNECTED state; then, the UE transmits a message to complete the setup procedure, such as an RRC setup complete message. At that point, the UE has an SRB which is setup (e.g., SRB1); then, before the UE finalizes the setup of the AS security (e.g., before AS security is activated), the UE receives from the network (e.g., from a gNodeB or 6G RAN node the UE is trying to connect to) an RRC message (e.g., RRC Reconfiguration) including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality).

[0129] Since in this case the UE expects to receive the RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality), e.g., the RRC message including the AI / ML configuration is required to be integrity protected and / or ciphered (encrypted), the reception of the RRC message before AS security is activated (e.g.,without ciphered and / or without integrity protection) triggers the UE to perform a recovery action. In one sub-option, the UE indicates a failure to the higher layers (e.g., AS indicates to the Non-Access Stratum layer at the UE), so that the upper layers (e.g., NAS layer) trigger a NAS recovery. In one sub-option, the triggering of a NAS recovery at NAS layer comprises the triggering of a Registration Area Update.

[0130] In one option, the UE is in RRC_CONNECTED, has the AS security activated and receives an RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality), which is not ciphered and / or is not integrity protected. And, since in this case the UE expects to receive the RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality), e.g., the RRC message including the AI / ML configuration is required to be integrity protected and / or ciphered (encrypted), the UE performs a recovery action. In one sub-option, the UE triggers an RRC procedure (e.g., an AS procedure). In one example, the RRC procedure is an RRC Re-establishment procedure. In one example, the RRC procedure is an RRC Resume procedure.

[0131] In one set of embodiments, the UE expects to receive an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) after security is activated (e.g., before the Access Stratum (AS) Security is activated) depending on a type of AI / ML configuration which is included. For example, when the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) includes an inference configuration the RRC message may be required to be integrity protected and / or ciphered (ciphered), but when other type of AI / ML configuration is included (e.g., applicability reporting configuration) the RRC message may not need to be integrity protected and / or ciphered (encrypted).

[0132] In another option, the UE is in RRC_CONNECTED and receives an RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) which is not ciphered and / or is not integrity protected, and that occurs before AS security is activated (and the RRC message including the AI / ML configuration associated with an AI / ML functionality is required to be integrity protected and / or ciphered (encrypted)), the UE performs a recovery action on an NAS level e.g., NAS recovery (like a Registration area update).

[0133] In another option, the UE is in RRC_CONNECTED and receives an RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) which is not ciphered and / or is not integrity protected, and that occurs after AS security is activated (and the RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) was required to be integrity protected and / or ciphered(encrypted)) the UE performs a recovery action on an AS level, e.g., an RRC re-establishment procedure.

[0134] Some embodiments can include log information about the failure. For example, Cause value = AI / ML included and message not secure.

[0135] Figure 8 illustrates a flowchart showing a method performed by a UE, e.g., UE 1212 in Figure 12 below, for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, in accordance with some embodiments. At block 810, the method comprises receiving, from a network node prior to activating Access Stratum, AS, security, a configuration for an AI / ML functionality. For example, the configuration for the AI / ML functionality may comprise a Radio Resource Control, RRC, message between the UE and a radio access network of the network node. In some embodiments, the configuration for the AI / ML functionality may comprise an unsecured message between the UE and the network node, e.g., a message including signaling information that is not protected by encryption and / or integrity checks. Functionally, the configuration for the AI / ML functionality may comprise one or more of the following: a configuration for the UE to perform AI / ML inference according to one or more AI / ML models or functionalities, a configuration for the UE to perform data collection for UE-side model training of one or more AI / ML models or functionalities, or a configuration for the UE to evaluate and report an applicability of one or more AI / ML models or functionalities.

[0136] In some embodiments, the configuration for the AI / ML functionality may be received by the UE after the UE transitions from an idle state to a connected state, and before one or more procedures for activating the AS Security are completed or initiated (e.g., after a message for activating the AS Security is received). In other embodiments, the configuration for the AI / ML functionality may be received from the network node before a message for activating the AS Security is received.

[0137] In some embodiments, in response to the configuration for the AI / ML functionality, the UE may send, to the network node, an indication that the configuration for the AI / ML functionality has been successfully applied. For example, the indication of a successful application may comprise an RRC Response message sent to the network node. The UE may also send an applicability indication for the AI / ML functionality to the network node in response to receiving the configuration. For example, the applicability indication may inform the radio access network whether the configuration for the AI / ML functionality applies to UE, e.g., applies to a current UE operating mode, location, etc. In some embodiments, the applicability indication for the AI / ML functionality may be transmitted based on when the ASsecurity is activated. For example, an applicability indication for the AI / ML functionality may be transmitted after the AS security is activated and may comprise at least one of an applicability reporting configuration or an inference configuration. As discussed above, the applicability reporting configuration may include one or more parameters, IE(s), fields and / or configuration(s) necessary and / or sufficient for the UE to evaluate and report the applicability of the AI / ML functionality.

[0138] At block 820, the method further comprises using the Al / ML functionality according to the received configuration to perform at least one action after the AS security mode is activated. For example, the at least one action may comprise performing one or more predictions of at least one of RRM measurements, measurement events, radio link failure, handover failure, or beam measurement related information for at least one of a serving cell, a neighbor cell, or a candidate cell; and transmitting, to the network node, a report comprising the one or more predictions after the AS security is activated.

[0139] Figure 9 illustrates a flowchart showing a method performed by a UE, e.g., UE 1212 in Figure 12 below, for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, in accordance with some embodiments. At block 910, the method comprises receiving, from a network node after activating Access Stratum, AS, security, a configuration for an AI / ML functionality.

[0140] In some embodiments, the configuration for the AI / ML functionality may comprise an RRC message. For example, the RRC message may be expected to be encrypted or integrity protected based on security keys derived during an activation procedure for the AS security. For example, the RRC message may be required (e.g., within the radio access network) to be ciphered, encrypted, or integrity protected. In some embodiments, the RRC message may be received after the UE transitions from an IDLE state to a CONNECTED state, and after an activation procedure for the AS security is completed or initiated. For example, the RRC message may comprise one or more data radio bearer, DRB, configurations applicable to a UE transition to a CONNECTED state.

[0141] In some embodiments, the method may further comprise receiving the configuration for the AI / ML functionality prior to activating the AS security mode and in response to triggering a recovery action. For example, the recovery action may comprise indicating a failure to higher layers or triggering a Non-Access Stratum, NAS, recovery procedure.

[0142] Alternatively, or additionally, the method may further comprise receiving an RRC message comprising the configuration for the AI / ML functionality after the AS security isactivated, and triggering a recovery action in response to the RRC message not being secured. For example, the recovery action in this scenario may comprise an RRC re-establishment procedure or an RRC resume procedure. Further, this scenario may include logging information about at least one failure upon triggering the recovery action, and transmitting, to the network node, a report comprising the information logged about the at least one failure.

[0143] At block 920, the method further comprises using the AI / ML functionality according to the received configuration to perform at least one action.

[0144] Figure 10 illustrates a flowchart showing a method performed by a network node, e.g., network node 1210 in Figure 12 below, for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, in accordance with some embodiments. At block 1010, the method comprises sending (e.g., transmitting), to a User Equipment, UE, prior to Access Stratum, AS, security being activated at the UE, a configuration for an AI / ML functionality, where the AI / ML functionality is used by the UE according to the received configuration to perform at least one action after the AS security mode is activated. For example, the configuration for the AI / ML functionality may comprise a Radio Resource Control, RRC, message between the network node (radio access network) and the UE. In some embodiments, the configuration for the AI / ML functionality may comprise an unsecured message between the network node and the UE, e.g., a message including signaling information that is not protected by encryption and / or integrity checks. Functionally, the configuration for the AI / ML functionality may comprise one or more of the following: a configuration for the UE to perform AI / ML inference according to one or more AI / ML models or functionalities, a configuration for the UE to perform data collection for UE-side model training of one or more AI / ML AI / ML models or functionalities, or a configuration for the UE to evaluate and report an applicability of one or more AI / ML models or functionalities.

[0145] In some embodiments, the configuration for the AI / ML functionality may be transmitted after the network node transitions the UE from an IDLE state to a CONNECTED state, and before one or more procedures for activating the AS Security are completed or initiated (e.g., after a message for activating the AS Security). In other embodiments, the configuration for the AI / ML functionality may be transmitted before transmitting, to the UE, a message for activating the AS Security.

[0146] In some embodiments, as shown at block 1020, the method may further comprise, in response to the configuration for the AI / ML functionality, receiving, from the UE, an indication that the configuration for the AI / ML functionality has been successfully applied, where the indication comprises an RRC Response message. Moreover, the method may furthercomprise, in response to the configuration for the AI / ML functionality, receiving, from the UE, an applicability indication for the AI / ML functionality. For example, the applicability indication for the AI / ML functionality may be transmitted based on when the AS security is activated and, e.g., may comprises at least one of an applicability reporting configuration, or an inference configuration.

[0147] In an embodiment, the at least one action may comprise the UE performing one or more predictions of at least one of RRM measurements, measurement events, Radio Link Failure, Handover Failure, or beam measurement related information for at least one of a serving cell, a neighbor cell, or a candidate cell. In some embodiments, as shown at block 1030, the method may further comprise receiving, from the UE, a report comprising the one or more predictions after the AS security is activated.

[0148] Figure 11 illustrates a flowchart showing a method performed by a network node, e.g., network node 1210 in Figure 12 below, for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, in accordance with some embodiments. At block 1110, the method comprises sending, to a UE after activating Access Stratum, AS, security, a configuration for an AI / ML functionality, where the AI / ML functionality is used by the UE according to the received configuration to perform at least one action at block 1120. For example, the configuration for the AI / ML functionality may comprise an RRC message, e.g., an RRC message that is expected to be encrypted or integrity protected based on security keys derived during an activation procedure for the AS security. For example, the RRC message may be transmitted after the network node transitions the UE from an IDLE state to a CONNECTED state, and after an activation procedure for the AS security is completed or initiated. In the case of a UE transitioning to a CONNECTED state, for example, the RRC message may comprise one or more data radio bearer, DRB, configurations. Further, in some embodiments, the RRC message may be required (e.g., by the radio access network) to be ciphered, encrypted, or integrity protected. In such cases, the method may further comprise receiving, from the UE, information about a failure when the UE receives an unsecured RRC message including the configuration for the AI / ML functionality.

[0149] Figure 12 shows an example of a communication system 1200 in accordance with some embodiments.

[0150] In the example, the communication system 1200 includes a telecommunication network 1202 that includes an access network 1204, such as a radio access network (RAN), and a core network 1206, which includes one or more core network nodes 1208. The access network 1204 includes one or more access network nodes, such as network nodes 1210a and1210b (one or more of which may be generally referred to as network nodes 1210), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points. Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 1202 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 1202 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 1202, including one or more network nodes 1210 and / or core network nodes 1208.

[0151] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O- CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al, Fl, Wl, El, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an O-2 interface defined by the O-RAN Alliance or comparable technologies. The network nodes 1210 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 1212a, 1212b, 1212c, and 1212d (one or more of which may be generally referred to as UEs 1212) to the core network 1206 over one or more wireless connections.

[0152] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 1200 may include any number of wired or wireless networks, network nodes, UEs,and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 1200 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0153] The UEs 1212 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1210 and other communication devices. Similarly, the network nodes 1210 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 1212 and / or with other network nodes or equipment in the telecommunication network 1202 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 1202.

[0154] In the depicted example, the core network 1206 connects the network nodes 1210 to one or more host computing systems, such as host 1216. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1206 includes one more core network nodes (e.g., core network node 1208) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 1208. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDE), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0155] The host 1216 may be under the ownership or control of a service provider other than an operator or provider of the access network 1204 and / or the telecommunication network 1202. The host 1216 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0156] As a whole, the communication system 1200 of Figure 12 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0157] In some examples, the telecommunication network 1202 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 1202 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 1202. For example, the telecommunications network 1202 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0158] In some examples, the UEs 1212 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 1204 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1204. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, e.g., being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN- DC).

[0159] In the example, the hub 1214 communicates with the access network 1204 to facilitate indirect communication between one or more UEs (e.g., UE 1212c and / or 1212d) and network nodes (e.g., network node 1210b). In some examples, the hub 1214 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1214 may be a broadband router enabling access to the core network 1206 for the UEs. As another example, the hub 1214 may be a controller that sends commands or instructions to one or more actuators in the UEs.Commands or instructions may be received from the UEs, network nodes 1210, or by executable code, script, process, or other instructions in the hub 1214. As another example, the hub 1214 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1214 may be a content source. For example, for a UE that is a VR device, display, loudspeaker, or other media delivery device, the hub 1214 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1214 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1214 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0160] The hub 1214 may have a constant / persistent or intermittent connection to the network node 1210b. The hub 1214 may also allow for a different communication scheme and / or schedule between the hub 1214 and UEs (e.g., UE 1212c and / or 1212d), and between the hub 1214 and the core network 1206. In other examples, the hub 1214 is connected to the core network 1206 and / or one or more UEs via a wired connection. Moreover, the hub 1214 may be configured to connect to an M2M service provider over the access network 1204 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1210 while still connected via the hub 1214 via a wired or wireless connection. In some embodiments, the hub 1214 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 1210b. In other embodiments, the hub 1214 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1210b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0161] Figure 13 shows a UE 1300 in accordance with some embodiments. The UE 1300 presents additional details of some embodiments of the UE 1212 of Figure 12. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage / playback device, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), an Augmented Reality (AR) or Virtual Reality (VR) device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device,etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0162] A UE may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle- to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0163] The UE 1300 includes processing circuitry 1302 that is operatively coupled via a bus 1304 to an input / output interface 1306, a power source 1308, a memory 1310, a communication interface 1312, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 13. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0164] The processing circuitry 1302 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 1310. The processing circuitry 1302 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 1302 may include multiple central processing units (CPUs).

[0165] In the example, the input / output interface 1306 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE1300. Examples of an input device include a touch-sensitive or presence- sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0166] In some embodiments, the power source 1308 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 1308 may further include power circuitry for delivering power from the power source 1308 itself, and / or an external power source, to the various parts of the UE 1300 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 1308. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 1308 to make the power suitable for the respective components of the UE 1300 to which power is supplied.

[0167] The memory 1310 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 1310 includes one or more application programs 1314, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1316. The memory 1310 may store, for use by the UE 1300, any of a variety of various operating systems or combinations of operating systems.

[0168] The memory 1310 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD- DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universalintegrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 1310 may allow the UE 1300 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 1310, which may be or comprise a device -readable storage medium.

[0169] The processing circuitry 1302 may be configured to communicate with an access network or other network using the communication interface 1312. The communication interface 1312 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1322. The communication interface 1312 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 1318 and / or a receiver 1320 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1318 and receiver 1320 may be coupled to one or more antennas (e.g., antenna 1322) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0170] In the illustrated embodiment, communication functions of the communication interface 1312 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0171] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 1312, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connectionto a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0172] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0173] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 1300 shown in Figure 13.

[0174] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, orother equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0175] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g., by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0176] Figure 14 shows a network node 1400 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0177] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0178] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0179] The network node 1400 includes a processing circuitry 1402, a memory 1404, a communication interface 1406, and a power source 1408. The network node 1400 may be composed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 1400 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 1400 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1404 for different RATs) and some components may be reused (e.g., a same antenna 1410 may be shared by different RATs). The network node 1400 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1400, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 1400.

[0180] The processing circuitry 1402 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node 1400 components, such as the memory 1404, to provide network node 1400 functionality.

[0181] In some embodiments, the processing circuitry 1402 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1402 includes one or more of radio frequency (RF) transceiver circuitry 1412 and baseband processing circuitry 1414. In some embodiments, the radio frequency (RF) transceiver circuitry 1412 and the baseband processing circuitry 1414 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 1412 and baseband processing circuitry 1414 may be on the same chip or set of chips, boards, or units.

[0182] The memory 1404 may comprise any form of volatile or non-volatile computer- readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM),read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computerexecutable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 1402. The memory 1404 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 1402 and utilized by the network node 1400. The memory 1404 may be used to store any calculations made by the processing circuitry 1402 and / or any data received via the communication interface 1406. In some embodiments, the processing circuitry 1402 and memory 1404 is integrated.

[0183] The communication interface 1406 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 1406 comprises port(s) / terminal(s) 1416 to send and receive data, for example to and from a network over a wired connection. The communication interface 1406 also includes radio front-end circuitry 1418 that may be coupled to, or in certain embodiments a part of, the antenna 1410. Radio front-end circuitry 1418 comprises filters 1420 and amplifiers 1422. The radio front-end circuitry 1418 may be connected to an antenna 1410 and processing circuitry 1402. The radio front-end circuitry may be configured to condition signals communicated between antenna 1410 and processing circuitry 1402. The radio front-end circuitry 1418 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 1418 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1420 and / or amplifiers 1422. The radio signal may then be transmitted via the antenna 1410. Similarly, when receiving data, the antenna 1410 may collect radio signals which are then converted into digital data by the radio front-end circuitry 1418. The digital data may be passed to the processing circuitry 1402. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0184] In certain alternative embodiments, the network node 1400 does not include separate radio front-end circuitry 1418, instead, the processing circuitry 1402 includes radio front-end circuitry and is connected to the antenna 1410. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1412 is part of the communication interface 1406. In still other embodiments, the communication interface 1406 includes one or more ports or terminals 1416, the radio front-end circuitry 1418, and the RF transceiver circuitry 1412, aspart of a radio unit (not shown), and the communication interface 1406 communicates with the baseband processing circuitry 1414, which is part of a digital unit (not shown).

[0185] The antenna 1410 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 1410 may be coupled to the radio frontend circuitry 1418 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1410 is separate from the network node 1400 and connectable to the network node 1400 through an interface or port.

[0186] The antenna 1410, communication interface 1406, and / or the processing circuitry 1402 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 1410, the communication interface 1406, and / or the processing circuitry 1402 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0187] The power source 1408 provides power to the various components of network node 1400 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1408 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1400 with power for performing the functionality described herein. For example, the network node 1400 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 1408. As a further example, the power source 1408 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0188] Embodiments of the network node 1400 may include additional components beyond those shown in Figure 14 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 1400 may include user interface equipment to allow input of information into the network node 1400 and to allow output of information from the network node 1400. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1400. In some embodiments providing a core network node, such as core network node108 of FIG. 12, some components, such as the radio front-end circuitry 1418 and the RF transceiver circuitry 1412 may be omitted.

[0189] Figure 15 is a block diagram illustrating a virtualization environment 1500 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 1500 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 1500 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface. Virtualization may facilitate distributed implementations of a network node, UE, core network node, or host.

[0190] Applications 1502 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0191] Hardware 1504 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 1506 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 1508a and 1508b (one or more of which may be generally referred to as VMs 1508), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 1506 may present a virtual operating platform that appears like networking hardware to the VMs 1508.

[0192] The VMs 1508 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 1506. Different embodiments of the instance of a virtual appliance 1502 may be implemented on oneor more of VMs 1508, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0193] In the context of NFV, a VM 1508 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 1508, and that part of hardware 1504 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs 1508 on top of the hardware 1504 and corresponds to the application 1502.

[0194] Hardware 1504 may be implemented in a standalone network node with generic or specific components. Hardware 1504 may implement some functions via virtualization. Alternatively, hardware 1504 may be part of a larger cluster of hardware (e.g., such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 1510, which, among others, oversees lifecycle management of applications 1502. In some embodiments, hardware 1504 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 1512 which may alternatively be used for communication between hardware nodes and radio units.

[0195] Additional embodiments are described below.EMBODIMENTSGroup A Embodiments1. A method performed by a user equipment for receiving an AI / ML configuration, the method comprising: receiving an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) before AS security is activated.2. The method of embodiment 1, wherein the AI / ML configuration (e.g., a configurationassociated to an AI / ML functionality) is received in an RRC message which is not secure.3. The method of embodiment 1 or 2, wherein the UE receives the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) after the UE transitions from an IDLE to a CONNECTED state, and before a procedure for setting up the Access Stratum (AS) Security is completed and / or initiated.4. The method of any of embodiments 1 to 3, wherein the UE receives the RRC message including the AI / ML configuration before the UE receives a message from the network (e.g., from a gNodeB or 6G RAN node) for setting up the AS security (e.g., before the UE receives a Security Mode Command message).5. The method of any of embodiments 1 to 4, wherein in response to the RRC message including the AI / ML configuration, transmitting to the network an RRC Response message (e.g., an RRC Reconfiguration Complete) to indicate that the UE has successfully applied the RRC message including the including the AI / ML configuration, wherein: the RRC response message (e.g., RRC Reconfiguration Complete) is transmitted before the AS security is activated or the RRC response message (e.g., RRC Reconfiguration Complete) is transmitted after the AS security is activated.6. The method of any of embodiments 1 to 5, wherein in response to the RRC message including the AI / ML configuration the UE transmits to the network an RRC Response message which includes an applicability indication for the AI / ML functionality.7. The method of any of embodiments 1 to 6, wherein the RRC response message including the applicability indication for the AI / ML functionality is transmitted before the AS security is activated or after the AS security is activated.8. The method of any of embodiments 1 to 7, wherein in response to the RRC message including the AI / ML configuration received before security is activated, transmitting to the network an applicability indication for the AI / ML functionality only after security is activated, wherein the UE transmits the applicability indication for the AI / ML functionality based on the AI / ML configuration including an applicability reporting configuration, or an inference configuration.9. The method of any of embodiments 1 to 8, wherein in response to the RRC message including the AI / ML configuration including an inference configuration, received before the AS security is activated, generating one or more inferences (e.g., predictions) as outputs of an AI / ML model and performing at least one action based on the generated inferences after the AS security is activated.10. The method of embodiment 9, wherein the one or more actions comprise at least one of:• Performing one or more predictions of RRM measurements for a serving cell and / or for a neighbor cell and / or for a candidate cell and reporting the one or more predictions of RRM measurements to the network in an RRC report message, wherein the RRC Report is transmitted by the UE only after AS security is activated;• Performing one or more predictions of measurement events for a serving cell and / or for a neighbor cell and / or for a candidate cell, and reporting the one or more predictions of RRM measurements to the network in an RRC report message, wherein the RRC Report is transmitted by the UE only after AS security is activated;• Performing one or more predictions of RLF and / or HOF for a serving cell and / or for a neighbor cell and / or for a candidate cell and reporting the one or more predictions in an RRC report message, wherein the RRC Report is transmitted by the UE only after AS security is activated;• Performing one or more predictions of beam measurement related information of a serving cell and / or for a neighbor cell and / or for a candidate cell and transmitting prediction(s) of beam measurement information to the network only after AS security is activated.11. The method of any of embodiments 1 to 10, wherein the AI / ML inference configuration is a configuration for the UE to perform AIML inference according to one or more AI / ML models / functionalities, a configuration for the UE to perform data collection for UE-side model training of one or more AIML models / functionalities, a configuration for the UE to evaluate and report the applicability of one or more AIML models / functionalities.12. A method performed by a user equipment for receiving an AI / ML configuration, the method comprising: receiving an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) after AS security is activated.13. The method of embodiment 12, wherein the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) is received in an RRC message.14. The method of embodiment 12, wherein an RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) is expected to be encrypted and / or is expected to be integrity protected based on security keys derived during an AS security activation procedure.15. The method of any of embodiments 12 to 14, wherein receiving the RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) occurs after the UE transitions from an IDLE to a CONNECTED state, and after the procedure for setting up the AS Security is completed and / or initiated.16. The method of any of embodiments 12 to 15, wherein receiving the RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) also includes the data radio bearers (DRBs) configuration(s).17. The method of any of embodiments 12 to 16, wherein the RRC message is required to be ciphered (encrypted) and / or integrity protected.18. The method of any of embodiments 12 to 17, further comprising receiving an RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) before AS security is activated and in response triggering a recovery action.19. The method of embodiment 18, wherein the recovery action comprises one or more of: indicating a failure to the higher layers; triggering a NAS recovery procedure.20. The method of any of embodiments 12 to 19, further comprising receiving an RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / MLfunctionality) after AS security is activated and, in response to the RRC message not being secured, triggering a recovery action.21. The method of embodiment 20, wherein the recovery action comprises an RRC reestablishment procedure or an RRC resume procedure.22. The method of any of embodiments 12 to 21, wherein upon triggering a recovery action logging information about the failure.23. The method of embodiment 22, further comprising reporting information about the failure.Group B Embodiments24. A method performed by a network node for transmitting an AI / ML configuration to a UE, the method comprising: transmitting an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) before AS security is activated at a UE.25. The method of embodiment 24, wherein the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) is transmitted in an RRC message which is not secure.26. The method of embodiment 24 or 25, wherein transmitting the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) occurs after the RAN node transitions the UE from an IDLE to a CONNECTED state, and before a procedure for setting up the AS Security is completed and / or initiated.27. The method of any of embodiments 24 to 26, wherein transmitting the RRC message including the AI / ML configuration occurs before the RAN node transmits a message from the network (e.g., from a gNodeB or 6G RAN node) for setting up the AS security (e.g., before the UE receives a Security Mode Command message).28. The method of any of embodiments 24 to 27, wherein in response to transmitting the RRC message including the AI / ML configuration, receiving from the UE an RRC Responsemessage (e.g., an RRC Reconfiguration Complete) to indicate that the UE has successfully applied the RRC message including the including the AI / ML configuration, wherein: the RRC response message (e.g., RRC Reconfiguration Complete) is received before the AS security is activated or the RRC response message (e.g., RRC Reconfiguration Complete) is received after the AS security is activated.29. The method of any of embodiments 24 to 28, wherein in response to transmitting the RRC message including the AI / ML configuration, receiving an RRC Response message which includes an applicability indication for the AI / ML functionality.30. The method of any of embodiments 24 to 29, wherein the RRC response message including the applicability indication for the AI / ML functionality is received before the AS security is activated or after the AS security is activated.31. The method of any of embodiments 24 to 30, wherein in response to transmitting the RRC message including the AI / ML configuration before security is activated, receiving an applicability indication for the AI / ML functionality after security is activated.32. The method of any of embodiments 24 to 31, wherein in response to transmitting the RRC message including the AI / ML configuration including an inference configuration before the AS security is activated, receiving a Report message from the UE including at least one information derived from an inference performed by the UE based on the AI / ML configuration, wherein the Report is received after security is activated.33. A method performed by a network node for transmitting an AI / ML configuration to a UE, the method comprising: transmitting an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) after AS security is activated.34. The method of embodiment 33, wherein the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) is transmitted in an RRC message.35. The method of embodiment 33, wherein an RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) is expected to beencrypted and / or is expected to be integrity protected based on security keys derived during an AS security activation procedure.36. The method of any of embodiments 33 to 35, wherein transmitting the RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) occurs after the RAN node transitions the UE from an IDLE to a CONNECTED state, and after the procedure for setting up the AS Security is completed and / or initiated.37. The method of any of embodiments 33 to 36, wherein transmitting the RRC message including the AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) also includes the data radio bearers (DRBs) configuration(s).38. The method of any of embodiments 33 to 37, wherein the RRC message is ciphered (encrypted) and / or integrity protected.39. The method of embodiment 33, further comprising receiving information about a failure when the UE receives an RRC message including an AI / ML configuration (e.g., a configuration associated to an AI / ML functionality) which is not secure.Group C Embodiments40. A user equipment, UE, for receiving an AI / ML configuration, comprising: processing circuitry configured to perform any of the steps of any of the Group A embodiments; and power supply circuitry configured to supply power to the processing circuitry.41. A network node for transmitting an AI / ML configuration, the network node comprising: processing circuitry configured to perform any of the steps of any of the Group B embodiments; power supply circuitry configured to supply power to the processing circuitry.42. A user equipment, UE, for receiving an AI / ML configuration, the UE comprising: an antenna configured to send and receive wireless signals; radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processingcircuitry; the processing circuitry being configured to perform any of the steps of any of the Group A embodiments; an input interface connected to the processing circuitry and configured to allow input of information into the UE to be processed by the processing circuitry; an output interface connected to the processing circuitry and configured to output information from the UE that has been processed by the processing circuitry; and a battery connected to the processing circuitry and configured to supply power to the UE.

[0196] Although the computing devices described herein (e.g., UEs, network nodes) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0197] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer- readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device -readable storage medium, such as in a hard-wired manner. In any of thoseparticular embodiments, whether executing instructions stored on a non-transitory computer- readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.REFERENCES1. RP-234039 - New WID on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface, Source: Qualcomm (Moderator), 3GPP TSG RAN Meeting #102, Edinburgh, Scotland, December 11-15, 20232. RP-234055, Study on Artificial Intelligence (AI) / Machine Learning (ML) for mobility in NR, 3GPP TSG RAN Meeting #102, Edinburgh, GB, December 11-15, 20233. R2-2406381 - Title: Report of [POST126]

[0032] [AI / ML PHY] LCM (Intel / Samsung)Phase 2, Source: Intel Corporation, 3GPP TSG RAN WG2 Meeting #127, Maastricht, Netherlands, Aug 19th- 23rd, 2024ABBREVIATIONSAt least some of the following abbreviations may be used in this disclosure. If there is an inconsistency between abbreviations, preference should be given to how it is used above. If listed multiple times below, the first listing should be preferred over any subsequent listing(s).

Claims

1. CLAIMS1. A method performed by a user equipment, UE, (1300) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, the method comprising:Receiving (810), from a network node (1400) prior to activating Access Stratum, AS, security, a configuration for an AI / ML functionality; andUsing (820) the AI / ML functionality according to the received configuration to perform at least one action after the AS security mode is activated.

2. The method of claim 1 , wherein the configuration for the AI / ML functionality comprises a Radio Resource Control, RRC, message.

3. The method of any of claims 1-2, wherein the configuration for the AI / ML functionality comprises an unsecured message.

4. The method of any of claims 1-3, wherein the configuration for the AI / ML functionality is received after the UE (1300) transitions from an IDLE state to a CONNECTED state, and before one or more procedures for activating the AS Security are completed or initiated.

5. The method of any of claims 1-4, wherein the configuration for the AI / ML functionality is received from the network node before a message for activating the AS Security is received.

6. The method of any of claims 1-5, wherein the method further comprises: in response to receiving the configuration for the AI / ML functionality, sending, to the network node (1400), an indication that the configuration for the AI / ML functionality has been successfully applied, wherein the indication comprises an RRC Response message.

7. The method of any of claims 1-6, wherein the method further comprises: in response to receiving the configuration for the AI / ML functionality, sending, to the network node, an applicability indication for the AI / ML functionality.

8. The method of claim 7, wherein the applicability indication for the AI / ML functionality is sent based on when the AS security is activated.

9. The method of claim 8, wherein the applicability indication for the AI / ML functionalityis transmitted after the AS security is activated and comprises at least one of the following: an applicability reporting configuration, or an inference configuration.

10. The method of any of claims 1-9, wherein the at least one action comprises at least one of the following: performing one or more predictions of at least one of RRM measurements, measurement events, Radio Link Failure, Handover Failure, or beam measurement related information for at least one of a serving cell, a neighbor cell, or a candidate cell; and sending, to the network node (1400), a report comprising the one or more predictions after the AS security is activated.

11. The method of any of claims 1-10, wherein the configuration for the AI / ML functionality comprises one or more of the following: a configuration for the UE to perform AI / ML inference according to one or more AI / ML models or functionalities, a configuration for the UE to perform data collection for UE-side model training of one or more AI / ML AI / ML models or functionalities, or a configuration for the UE to evaluate and report an applicability of one or more AI / ML models or functionalities.

12. A method performed by a user equipment, UE, (1300) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, the method comprising:Receiving (910), from a network node (1400) after activating Access Stratum, AS, security, a configuration for an AI / ML functionality; andUsing (920) the AI / ML functionality according to the received configuration to perform at least one action.

13. The method of claim 12, wherein the configuration for the AI / ML functionality comprises an RRC message.

14. The method of claim 13, wherein the RRC message is expected to be encrypted or integrity protected based on security keys derived during an activation procedure for the AS security.

15. The method of any of claims 12-14, wherein the RRC message is received after the UE transitions from an IDLE state to a CONNECTED state, and after an activation procedure for the AS security is completed or initiated.

16. The method of any of claims 12-15, wherein the RRC message comprises one or more data radio bearer, DRB, configurations.

17. The method of any of claims 12-16, wherein the RRC message is required to be ciphered, encrypted, or integrity protected.

18. The method of any of claims 11-17, further comprising receiving the configuration for the AI / ML functionality prior to activating the AS security mode and in response to triggering a recovery action.

19. The method of claim 18, wherein the recovery action comprises at least one of the following: indicating a failure to higher layers; or triggering a Non-Access Stratum, NAS, recovery procedure.

20. The method of any of claims 11-19, further comprising: receiving an RRC message comprising the configuration for the AI / ML functionality after the AS security is activated; and triggering a recovery action in response to the RRC message not being secured.

21. The method of claim 20, wherein the recovery action comprises an RRC re-establishment procedure or an RRC resume procedure.

22. The method of any of claims 20-21, further comprising: logging information about at least one failure upon triggering the recovery action.

23. The method of embodiment 22, further comprising: sending, to the network node (1400), a report comprising the information logged about the at least one failure.

24. A method performed by a network node (1400) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, the method comprising:Sending (1010), to a User Equipment, UE, (1300) prior to Access Stratum, AS, security being activated at the UE, a configuration for an AI / ML functionality, wherein the AI / ML functionality is used (920) by the UE (1300) according to the received configuration to perform at least one action after the AS security mode is activated.

25. The method of claim 24, wherein the configuration for the AI / ML functionality comprises a Radio Resource Control, RRC, message.

26. The method of any of claims 24-25, wherein the configuration for the AI / ML functionality comprises an unsecured message.

27. The method of any of claims 24-26, wherein the configuration for the AI / ML functionality is sent after the network node (1400) transitions the UE (1300) from an IDLE state to a CONNECTED state, and before one or more procedures for activating the AS Security are completed or initiated.

28. The method of any of claims 24-27, wherein the configuration for the AI / ML functionality is sent before transmitting, to the UE (1300), a message for activating the AS Security.

29. The method of any of claims 24-28, wherein the method further comprises: in response to the configuration for the AI / ML functionality, receiving (1020), from the UE (1300), an indication that the configuration for the AI / ML functionality has been successfully applied, wherein the indication comprises an RRC Response message.

30. The method of any of claims 24-29, wherein the method further comprises: in response to the configuration for the AI / ML functionality, receiving, from the UE (1300), an applicability indication for the AI / ML functionality.

31. The method of claim 30, wherein the applicability indication for the AI / ML functionalityis sent based on when the AS security is activated.

32. The method of claim 31 , wherein the applicability indication for the AI / ML functionality is received after the AS security is activated and comprises at least one of the following: an applicability reporting configuration, or an inference configuration.

33. The method of any of claims 24-32, wherein the at least one action comprises the UE (1300) performing one or more predictions of at least one of RRM measurements, measurement events, Radio Link Failure, Handover Failure, or beam measurement related information for at least one of a serving cell, a neighbor cell, or a candidate cell.

34. The method of claim 33, further comprising:Receiving (1030), from the UE (1300), a report comprising the one or more predictions after the AS security is activated.

35. The method of any of claims 24-34, wherein the configuration for the AI / ML functionality comprises one or more of the following: a configuration for the UE (1300) to perform AI / ML inference according to one or more AI / ML models or functionalities, a configuration for the UE (1300) to perform data collection for UE-side model training of one or more AI / ML AI / ML models or functionalities, or a configuration for the UE (1300) to evaluate and report an applicability of one or more AI / ML models or functionalities.

36. A method performed by a network node for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, the method comprising: sending (1110), to a UE (1300) after activating Access Stratum, AS, security, a configuration for an AI / ML functionality, wherein the AI / ML functionality is used (1120) by the UE (1300) according to the received configuration to perform at least one action.

37. The method of claim 36, wherein the configuration for the AI / ML functionality comprises an RRC message.

38. The method of claim 37, wherein the RRC message is expected to be encrypted or integrity protected based on security keys derived during an activation procedure for the AS security.

39. The method of any of claims 37-38, wherein the RRC message is sent after the network node transitions the UE (1300) from an IDLE state to a CONNECTED state, and after an activation procedure for the AS security is completed or initiated.

40. The method of any of claims 37-39, wherein the RRC message comprises one or more data radio bearer, DRB, configurations.

41. The method of any of claims 37-40, wherein the RRC message is required to be ciphered, encrypted, or integrity protected.

42. The method of claim 41, further comprising: receiving, from the UE (1300), information about a failure when the UE (1300) receives an unsecured RRC message including the configuration for the AI / ML functionality.

43. A user equipment, UE, (1300) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, comprising: processing circuitry configured to perform one or more steps comprising at least one of: receiving, from a network node (1400) prior to activating Access Stratum, AS, security, a configuration for an AI / ML functionality; and using the AI / ML functionality according to the received configuration to perform at least one action after the AS security mode is activated; and power supply circuitry configured to supply power to the processing circuitry.

44. A user equipment, UE, (1300) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, comprising: processing circuitry configured to perform one or more steps comprising at least one of: receiving, from a network node (1400) after activating Access Stratum, AS,security, a configuration for an AI / ML functionality; and using the AI / ML functionality according to the received configuration to perform at least one action; and power supply circuitry configured to supply power to the processing circuitry.

45. A network node (1400) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, the network node (1400) comprising: processing circuitry configured to perform one or more steps comprising at least one of: sending, to a User Equipment, UE, (1300) prior to Access Stratum, AS, security being activated at the UE (1300), a configuration for an AI / ML functionality, wherein the AI / ML functionality is used by the UE (1300) according to the received configuration to perform at least one action after the AS security mode is activated; and power supply circuitry configured to supply power to the processing circuitry.

46. A network node (1400) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, the network node (1400) comprising: processing circuitry configured to perform one or more steps comprising at least one of: sending, to a User Equipment, UE, (1300) prior to Access Stratum, AS, security being activated at the UE (1300), a configuration for an AI / ML functionality, wherein the AI / ML functionality is used by the UE (1300) according to the received configuration to perform at least one action after the AS security mode is activated; and power supply circuitry configured to supply power to the processing circuitry.

47. A user equipment, UE, (1300) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, the UE (1300) comprising: an antenna configured to send and receive wireless signals; radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry; the processing circuitry being configured to perform one or more steps comprising: receiving, from a network node (1400) prior to activating Access Stratum, AS, security, a configuration for an AI / ML functionality; andusing the AI / ML functionality according to the received configuration to perform at least one action after the AS security mode is activated; the processing circuitry and configured to allow input of information into the UE (1300) to be processed by the processing circuitry; an output interface connected to the processing circuitry and configured to output information from the UE (1300) that has been processed by the processing circuitry; and a battery connected to the processing circuitry and configured to supply power to the UE (1300).

48. A user equipment, UE, (1300) for configuring an Artificial Intelligence / Machine Learning, AI / ML, functionality, the UE (1300) comprising: an antenna configured to send and receive wireless signals; radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry; the processing circuitry being configured to perform one or more steps comprising: receiving, from a network node after activating Access Stratum, AS, security, a configuration for an AI / ML functionality; and using the AI / ML functionality according to the received configuration to perform at least one action; the processing circuitry and configured to allow input of information into the UE (1300) to be processed by the processing circuitry; an output interface connected to the processing circuitry and configured to output information from the UE (1300) that has been processed by the processing circuitry; and a battery connected to the processing circuitry and configured to supply power to the UE (1300).

Images