Privacy service in o-ran to enable data privacy protection and secure data transfer

Abstract

The present disclosure relates to performing a privacy service in Open Radio Access Network (O-RAN). Input data, information related to a privacy-preserving technique selected from a plurality of privacy-preserving techniques, and information associated with at least one recipient are received at a secure communication interface coupled to the O-RAN. The information related to the privacy-preserving technique comprises a type and a plurality of parameters associated with the technique. The method further includes transforming the input data based on the information related to the privacy-preserving technique to obtain privacy-preserved output data. The privacy-preserved output data is then transmitted to the at least one recipient through the secure communication interface.

Description

PRIVACY SERVICE IN O-RAN TO ENABLE DATA PRIVACY PROTECTION AND SECURE DATA TRANSFERCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to Indian Provisional Patent Application Number 202541013748, filed on February 18, 2025, and Indian Non-Provisional Patent Application Number 202541013748, filed on August 26, 2025, the entire contents of which are incorporated herein by reference.TECHNICAL FIELD

[0002] The present disclosure relates to privacy service in O-RAN to enable data privacy protection and secure data transfer.BACKGROUND

[0003] Open Radio Access Network (O-RAN) allows interoperation between cellular network equipment provided by different vendors. O-RAN enables intelligent RAN control by using RAN Intelligent Controllers (RICs). The RICs include Near-Real Time (RT) and Non-RT RICs. The applications such as xApps (Extended Application) and rApps (here 'r' stands for RAN) are implemented in Near-RT RIC and Non-RT RIC, respectively. These applications expand the intelligent RAN control capabilities of O-RAN.

[0004] The advancement in O-RAN architecture enables a virtualized and disaggregated environment. The O-RAN manages RAN using the xApps and the rApps. These applications may access sensitive data from various entities such as the RAN, User Equipment (UEs), and the like. This increases the risk of unauthorized data exposure.

[0005] The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the disclosure and should not be taken as acknowledgment or any form of suggestion that this information forms prior art already known to a person skilled in the art.SUMMARY:

[0006] In an embodiment, the present disclosure provides a method for privacy service in Open Radio Access Network (O-RAN) to enable data privacy protection and secure data transfer. The method includes receiving, at a secure communication interface coupled to the O-RAN, input data, information related to a privacy-preserving technique selected from a plurality of privacy-preserving techniques, and information associated with at least one recipient. The information related to the privacy -preserving technique comprises a type and a plurality of parameters associated with the technique. The method further includes transforming the input data based on the information related to the privacy-preserving technique to obtain privacy-preserved output data. The privacy-preserved output data is then transmitted to the at least one recipient through the secure communication interface.

[0007] In another embodiment, the present disclosure provides an apparatus for privacy sen ice in O-RAN to enable data privacy protection and secure data transfer. The apparatus is configured to receive, at a secure communication interface coupled to the O-RAN, input data, information related to a privacy-preserving technique selected from a plurality of privacypreserving techniques, and information associated with at least one recipient. The information related to the privacy-preserving technique comprises a type and a plurality of parameters associated with the technique. The method further includes transforming the input data based on the information related to the privacy-preserving technique to obtain privacy-preserved output data. The privacy -preserved output data is then transmitted to the at least one recipient through the secure communication interface.

[0008] In another embodiment, the present disclosure provides a non-transitory computer readable medium including instructions for performing operations including receiving, at a secure communication interface coupled to the O-RAN, input data, information related to a privacy-preserving technique selected from a plurality of privacy-preserving techniques, and information associated with at least one recipient. The information related to the privacypreserving technique comprises a type and a plurality of parameters associated with the technique. The method further includes transforming the input data based on the information related to the privacy-preserving technique to obtain privacy-preserved output data. The privacy -preserved output data is then transmitted to the at least one recipient through the secure communication interface.

[0009] The present disclosure provides a mechanism for implementing privacy -preserving techniques within 0-RAN and eliminates the need for individual network functions to independently implement complex privacy -preserving algorithms. Computational overhead on resource-constrained network functions is reduced and consistent application of privacy policies across heterogeneous O-RAN components is enabled. Additionally, the capability to transmit privacy-preserved output data to intended recipients through the secure communication interface enables end-to-end confidentiality and integrity of sensitive information.

[0010] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description. For a better understanding of exemplary embodiments of the present disclosure, together with other and further features and advantages thereof, reference is made to the following description, taken in conjunction with the accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The embodiments of the disclosure itself, as well as a preferred mode of use, further objectives, and advantages thereof, will best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying drawings. One or more embodiments are now described, by way of example only, with reference to the accompanying drawings in which:

[0012] Figure 1 illustrates a conventional Open Radio Access Network (O-RAN) architecture;

[0013] Figure 2 illustrates an exemplary block diagram of an apparatus for performing data privacy procedures in O-RAN, in accordance with some embodiments of the present disclosure;

[0014] Figures 3A-B and 4A-B illustrate exemplary flow diagrams illustrating data privacy procedures in O-RAN, in accordance with an embodiment of the present disclosure; and

[0015] Figure 5 illustrates a method for performing data privacy procedures in O-RAN, in accordance with embodiments of the present disclosure.

[0016] The figures depict embodiments of the disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.DESCRIPTION OF THE DISCLOSURE

[0017] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0018] While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the spirit and the scope of the disclosure.

[0019] The terms “comprises’', “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a device or system or apparatus proceeded by “comprises... a” does not. without more constraints, preclude the existence of other elements or additional elements in the device or system or apparatus.

[0020] In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0021] The advancement in Open Radio Access Network (O-RAN) architecture enables a virtualized and disaggregated environment. The O-RAN manages Radio Access Network (RAN) using the xApps and the rApps. These applications may access sensitive data from various entities such as the RAN, User Equipment (UEs). and the like. This increases the risk of unauthorized data exposure.

[0022] Privacy handling of data is not implemented in O-RAN architecture elements as a service. The current O-RAN architecture uses known privacy preserving techniques, such as, homomorphic encryption, federated learning for Machine Learning (ML), differential privacy, secure multi-party computing, etc. Some existing systems use Inner Product Functional Encryption (IPFE) for preserving privacy of data in RAN Intelligent Controller (RIC) platform. However, the privacy’ as a service is not implemented in the current O-RAN architecture.

[0023] In multi-vendor O-RAN deployments, each network function may need to independently implement privacy-preserving techniques, leading to inconsistencies and increased complexity.

[0024] In some cases, a Network Function (NF) or application implementing the functionality of the NF may not be equipped to perform the privacy preservation due to lack of required software, or it lacks computational power or storage resources. In such case, a privacy service from a trusted network function or platform or entity is required to offload the task of privacy preser ation.

[0025] The present disclosure provides a privacy sendee which provides data handling capabilities to preserve privacy and can also perform secure transfer of privacy-protected or privacy -preserved data to intended parties (within or external to O-RAN).

[0026] The present disclosure provides a method and apparatus for performing data privacy procedures in O-RAN. The technical solution includes receiving, at a secure communication interface coupled to the O-RAN, input data, information related to a privacy-preserving technique selected from a plurality of privacy-preserving techniques, and information associated with at least one recipient. The information related to the privacy -preserving technique comprises a type and a plurality’ of parameters associated with the technique. The method further includes transforming the input data based on the information related to the privacy-preserving technique to obtain privacy-preserved output data. The privacy-preservedoutput data is then transmitted to the at least one recipient through the secure communication interface.

[0027] The present provides a technical advantage by providing a mechanism for implementing privacy -preserving techniques within 0-RAN and eliminates the need for individual network functions to independently implement complex privacy-preserving algorithms. Computational overhead on resource-constrained network functions is reduced and consistent application of privacy policies across heterogeneous 0-RAN components is enabled. Additionally, the capability to transmit privacy -preserved output data to intended recipients through the secure communication interface enables end-to-end confidentiality and integrity of sensitive information.

[0028] As used herein, the term “privacy-preserving technique” may refer to a computational method applied to input data to protect confidentiality or prevent unauthorized inference during processing or transmission.

[0029] As used herein, the term “type” may refer to a specific category or class of the privacypreserving technique. Examples of type of privacy-preserving techniques include, without limitation, federated learning, differential privacy, Secure Multi-Part}' Computing (SMPC), Homomorphic Encryption and such.

[0030] As used herein, the term “plurality of parameters” may refer to a set of configuration values associated with the privacy -preser ing technique, that define operational characteristics for execution of the privacy-preserving technique. Examples of such parameters include, without limitation, epsilon and delta for differential privacy, learning rate and number of training rounds for federated learning, etc.

[0031] As used herein, the term “secure communication interface” may refer to a communication interface configured to exchange data and control information over a protected channel between entities in an 0-RAN environment. Examples include a HyperText Transfer Protocol Secure based (HTTPS-based) Application Programming Interface (API) endpoint with Transport Layer Security (TLS) encryption for transmitting input data and privacy-preserved output data.

[0032] As used herein, the term “privacy-preserved output data” may refer to data that has been transformed using a privacy-preserving technique. Examples of privacy-preserved output datainclude, without limitation, encrypted data generated using homomorphic encryption, noise-added data generated using differential privacy, an aggregated ML model generated using federated learning, etc.

[0033] Figure 1 illustrates a conventional O-RAN architecture. RIC is a component of the O-RAN architecture that is responsible for controlling and optimizing RAN functions. The RIC enables multivendor interoperability, intelligence, agi 1 i ty , and programmability to RANs. A non-RealTime RIC (non-RT RIC) is hosted by Service Management and Orchestration (SMO) framework. The near-Real-Time RIC (near-RT RIC) can be co-located with Third Generation Partnership Project (3GPP) Next Generation Node B (gNodeB) functions, namely, O-RAN-compliant Central Unit (O-CU) and / or Distributed Unit (O-DU) (shown as E2 Node(s) in Figure 1) or fully decoupled from them.

[0034] xApp (extended Application) is used by the near-RT RIC to implement specific functions or sendees in near-real time within the O-RAN architecture. These applications or services include functions like radio resource management, mobility management, security, and the like. There are multiple xApps to manage various radio control functions, as illustrated in Figure 1. The xApps are typically deployed on top of the near-RT RIC and communicates with other components over E2 interface within the O-RAN architecture. xApps also include an internal messaging framework to handle conflict mitigation, subscription management, application lifecycle management functions, security, and the like. These components are known in the existing O-RAN architecture, and are thus not explained for sake of brevity. In the O-RAN architecture, each disaggregated network function, such as O-CU-CP, O-CU-UP, and O-DU of a gNB, or an O-eNB, as well as the combination of O-CU-CP, O-CU-UP, O-DU, or the Near-RT RIC, is referred to as an E2 node. E2 nodes support E2 interface towards near RT-RIC and 01 interface towards SMO.

[0035] The present disclosure discloses enabling privacy as a service in the O-RAN architecture. The present disclosure identifies different interfaces or senice endpoints implemented by the privacy sendee. The privacy senice receives the data to be protected for privacy, privacy preserving technique to be applied, endpoint(s) details of the intended recipients of the private data. The privacy service performs the privacy preservation on the data and then transfers the data or a model to the endpoint of the intended recipients.

[0036] FIGURE 2 illustrates an embodiment of an apparatus 200. As show n in FIGURE 2, the apparatus 200 comprises a processor 202. a memory 204, a storage component 206. an input component 208, an output component 210, a communication interface 212, and a bus 214. The apparatus 200 may be used for implementing privacy sendee in O-RAN to enable data privacy protection and secure data transfer.

[0037] The processor 202, as used herein, means any type of computational circuit that may comprise hardware elements and software elements. The processor 202 may be embodied as a multi-core processor, a single core processor, or a combination of one or more multi-core processors and / or one or more single core processors, a distributed processing system, or the like. The processor 202 may be a Central Processing Unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), an application-specific integrated circuit (ASIC), or another type of processing component.

[0038] The memory 204 includes a non-transitory computer readable medium. Memory 204 includes a random- access memory (RAM), a read only memory (ROM), and / or another type of dynamic or static storage device (e.g., a flash memory, a magnetic memory, and / or an optical memory) that stores information and / or instructions for use by processor 202. The memory 204 comprises machine-readable instructions which are executable by the processor 202. These machine-readable instructions when executed by the processor 202 cause the processor 202 to perform one or more method steps of an embodiment described above. The memory 204 may be used to realize the memory. The memory is communicatively coupled to the processor 202. The memory 204 stores instructions, executable by the one or more processors 202, which, on execution, may cause the processor 202 to implement performing data privacy procedures in O-RAN, in accordance with embodiments of the present disclosure.

[0039] The storage component stores information and / or software related to the operation and use of the apparatus 200. For example, the storage component 206 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, and / or a solid-state disk), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, and / or another type of non-transitory computer-readable medium, along with a corresponding drive.

[0040] The input component is configured to receive information, such as user input. For example, the input component may include, but not be limited to, a touch screen display, akeyboard, a keypad, a mouse, a button, a switch, and / or a microphone. Additionally, or alternatively, the input component 208 may include a sensor for sensing information (e.g., a global positioning system (GPS), an accelerometer, a gyroscope, and / or an actuator).

[0041] The output component is configured to provide output information from the apparatus 200. For example, the output component may be, but not limited to, a display, a speaker, instructions to an external device, and / or one or more light-emitting diodes (LEDs).

[0042] The communication interface is an interface that provides a communication connection to other devices, such as external devices and internal devices. The connection by the communication interface can be a wired connection, a wireless connection, or a combination of wired and wireless connections, and can be a direct connection or an indirect connection via a communication network that exists between the apparatus 200 and other devices. In other w ords, the standard of the communication interface is not limited.

[0043] The bus 214 acts as an interconnect between the processor, the memory, the storage component 206, the input component 208. the output component 210, and the communication interface 212 of the apparatus 200. The bus 214 may include a wired interconnection or a wireless interconnection.

[0044] The processor 202 performs the step of receiving, at a secure communication interface communicatively coupled to Open Radio Access Network (O-RAN), input data, an information related to a privacy-preser ing technique from a plurality of privacy-preser ing techniques, and information associated with at least one recipient. The information related to the privacypreserving technique comprises a type and a plurality of parameters associated with the privacy -preserving technique.

[0045] The processor 202 performs the step of transforming the input data based on the information related to the privacy-preserving technique, to obtain privacy-preserved output data.

[0046] The processor 202 performs the step of transmitting the privacy-preserved output data to the at least one recipient through the secure communication interface.

[0047] Figures 3A and 3B illustrates an exemplary flow diagram illustrating data privacy procedures in O-RAN, in accordance with embodiments of the present disclosure.

[0048] The method may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract data types.

[0049] The order in which the method is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0050] The functionality or the steps performed by the privacy service are explained in detail. At step 301, a secure communication interface communicatively coupled to O-RAN is exposed for receiving input data, information related to a privacy -preserving technique, and information associated with at least one recipient. As shown in Figure 3A, a secure service endpoint is exposed by the privacy service for data ingestion.

[0051] At step 302, the secure service endpoint receives, from a service consumer, the input data, the information related to the privacy-preserving technique comprising a type and a plurality of parameters, and the information associated with the at least one recipient. As shown in Figure 3A, the service consumer transmits plain / raw data, the privacy -preserving technique, parameters, and protocol and communication parameters of the intended recipients

[0052] The next steps are performed only if required by the selected privacy-preserving technique, such as federated learning. Steps 303 to 305 are executed until a training completion indication is received as true.

[0053] At step 303, when the privacy-preserving technique is federated learning, the input data or an aggregated model is transmitted to a federated learning service for generating a partial ML model. As shown in Figure 3A, the privacy service provides raw data (first time) or an aggregated model (subsequently) to the federated learning service to obtain a partial (shared) model.

[0054] At step 304, the federated learning ser ice transmits the partial ML model to a federated learning central server for aggregation. At step 305, the federated learning central server transmits an aggregated ML model and a training completion indication to the federated learning service. As shown in Figure 3A, the federated learning central server returns the aggregated model and the training complete indication (true or false).

[0055] At step 306, upon completion of federated learning, the aggregated ML model is transmitted from the privacy service to the at least one recipient through the secure communication interface. As shown in Figure 3B, the privacy service sends the aggregated model to the processed data / model consumer.

[0056] Steps 307 to 311 are executed until data processing using the privacy -preserving technique is completed.

[0057] At step 307, the input data is transformed based on the privacy-preserving technique to obtain privacy-preserved output data. As shown in Figure 3B, the privacy service performs processing to obtain privacy-preserved data using the provided technique.

[0058] At step 308, when required by the privacy-preserving technique, a session identifier and a callback endpoint are generated for managing subsequent requests from the at least one recipient. As shown in Figure 3B, the privacy service creates a session and callback endpoint to manage subsequent requests.

[0059] At step 309, the privacy-preserved output data is transmitted to the at least one recipient through the secure communication interface. As shown in Figure 3B, the privacy service securely transfers the processed data or model to the consumer.

[0060] At step 310, when required by the privacy-preserving technique, a callback message is received from the at least one recipient at the callback endpoint. As shown in Figure 3B, the processed data / model consumer sends a callback message to the privacy service.

[0061] At step 311, the callback message is processed based on the privacy -preserving technique. As shown in Figure 3B, the privacy service processes the payload according to the current privacy-preserving technique.

[0062] In an embodiment, the privacy service may be implemented in O-Cloud, SMO, RIC platform or any other system within O-RAN or external to 0-RAN. In an embodiment, the service consumer and the data consumer may be the same where the processed (anonymized) data is sent back to the service consumer.

[0063] Figures 4A and 4B illustrate exemplary embodiments of the present disclosure. Figure 4A depicts an embodiment of the present disclosure using Near-RT RIC as the host of the privacy service and E2 nodes as service consumer providing the plain / raw data. The privacy preserving technique is “Differential privacy’' with xApps as the data recipients. At step 401, a secure communication interface communicatively coupled to O-RAN is exposed for receiving input data, information related to a privacy-preserving technique, and information associated with at least one recipient. As shown in Figure 4 A, a secure service endpoint (e.g., HyperText Transfer Protocol (HTTP) POST with JavaScript Object Notation (JSON) input) is exposed for data ingestion.

[0064] At step 402, the secure communication interface receives, from an E2 Node acting as a service consumer, the input data, the information related to the privacy-preserving technique comprising a type and a plurality of parameters, and the information associated with the at least one recipient. As shown in Figure 4A, the E2 Node transmits a sample input including the privacy -preserving technique “differential privacy,” parameters {epsilon=x, delta=d], a consumer callback address, and the data.

[0065] At step 403, the input data is transformed based on the privacy -preserving technique to obtain privacy-preserved output data. As shown in Figure 4A, noise is introduced to the data based on the epsilon and delta parameters.

[0066] At step 404, the privacy-preserved output data is transmitted to the at least one recipient through the secure communication interface. As shown in Figure 4A, the Near-RT RIC securely transfers the processed differential privacy data to the xApp acting as the processed model consumer.

[0067] Figure 4B depicts an embodiment of the present disclosure using Near-RT RIC as the host of the privacy service, non-RT RIC as the host of federated learning service, an external server as the central server aggregating the partial models received and E2 nodes providing theplain / raw data. The privacy preserving technique is “Federated learning” with xApp as the final model recipient.

[0068] At step 405, a secure communication interface communicatively coupled to O-RAN is exposed for receiving input data, information related to a privacy-preserving technique, and information associated with at least one recipient. As shown in Figure 4B, a secure senice endpoint (e.g., HTTP POST with JSON input) is exposed for data ingestion.

[0069] At step 406, the secure communication interface receives, from an E2 Node acting as a service consumer, the input data, the information related to the privacy-preserving technique comprising a type and a plurality of parameters, and the information associated with the at least one recipient. As shown in Figure 4B, the E2 Node transmits a sample input including the privacy -preserving technique “federated learning,” parameters {leaming_rate=0.001}, a consumer callback address, and the data.

[0070] At step 407, the input data and model parameters are transmitted to a federated learning service for generating a partial ML model. As shown in Figure 4B, the Near-RT R1C transmits the data, model parameters, and Federated Learning (FL) central server details to the Non-RT RIC acting as the federated learning service. Steps 408 to 410 are executed until a training completion indication is received as true.

[0071] At step 408, the federated learning service prepares a partial ML model based on the input data and parameters. As show n in Figure 4B, the Non-RT RIC prepares the partial model based on the data and parameters. At step 409, the federated learning service transmits the partial ML model to an external federated learning central server for aggregation.

[0072] At step 410, the federated learning central server aggregates the partial models received from multiple participants. At step 411, the federated learning central server transmits an aggregated ML model and a training completion indication to the federated learning service. As show n in Figure 4B, the external federated learning central server shares the aggregated model and the training complete indication (true or false) securely with the Non-RT RIC.

[0073] At step 412, upon completion of federated learning, the aggregated ML model is transmitted from the privacy service to the at least one recipient through the secure communication interface. As shown in Figure 4B. the Near-RT RIC securely transfers the aggregated model to the xApp acting as the processed model consumer.

[0074] In this embodiment, the central federated learning server may be external and not within the trust boundaries of O-RAN since the data to be protected is not shared with the central server and only partial models are shared. Also, the privacy service can pass the central server participating in the federated learning as a parameter to federated learning service.

[0075] The present disclosure provides a privacy service which provides data handling capabilities to preserve privacy and can also perform secure transfer of privacy-protected or privacy-preserved data to intended parties (within or external to O-RAN). The present disclosure enables data privacy protection and secure data transfer in O-RAN.

[0076] FIGURE 5 illustrates a method for performing data privacy procedures in O-RAN, in accordance with embodiments of the present disclosure. As illustrated in Figure 5, the method 500 may comprise one or more steps.

[0077] The order in which the method 500 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0078] At step 502, the method receives, at a secure communication interface communicatively coupled to O-RAN, input data, an information related to a privacy -preserving technique from a plurality of privacy-preserving techniques, and information associated with at least one recipient, wherein the information related to the privacy -preserving technique comprises a type and a plurality of parameters associated with the privacy-preserving technique. At step 504, the method transforms the input data based on the information related to the privacy -preserving technique, to obtain privacy -preserved output data.

[0079] At step 506, the method transmits the privacy-preserved output data to the at least one recipient through the secure communication interface.

[0080] The method provides a technical advantage by providing a mechanism for implementing privacy-preserving techniques within O-RAN and eliminates the need for individual network functions to independently implement complex privacy-preservingalgorithms. Computational overhead on resource-constrained network functions is reduced and consistent application of privacy policies across heterogeneous O-RAN components is enabled. Additionally, the capability to transmit privacy-preserved output data to intended recipients through the secure communication interface enables end-to-end confidentiality and integrity of sensitive information.

[0081] In some non-limiting embodiments, the method further includes selectively retaining or discarding the input data, based on a policy associated with the privacy -preserving technique. The process comprises evaluating a policy that is associated with the type and the plurality of parameters of the privacy-preserving technique, and, responsive to the evaluation, storing the input data for an authorized retention interval or deleting the input data after transformation. Thereby, the risk of unauthorized exposure of data is reduced.

[0082] As described above, selective retention or discarding of the input data is executed based on a policy associated with the privacy -preserving technique.

[0083] In some non-limiting embodiments, the privacy-preserving technique is federated learning and the transforming comprises (a) transmitting the input data associated with a plurality of recipients to a federated learning server for performing training on the input data and generating a plurality of partial ML models, and (b) transmitting an aggregated ML model, that is generated based on the plurality of partial ML models, to the plurality of recipients. Offloading training orchestration to a federated learning server improves coordination across participants, thereby improving training throughput and facilitating consistent model aggregation.

[0084] As described above, the transmission of input data to a federated learning server for generating partial ML models and the subsequent transmission of an aggregated ML model to the plurality of recipients are executed as part of the transforming. Thereby, scalability of collaborative learning within O-RAN is improved.

[0085] In some non-limiting embodiments, the method further includes generating a session identifier and a callback endpoint for the at least one recipient, and processing a callback message received on the callback endpoint based on the privacy-preserving technique. The session identifier and callback endpoint enable asynchronous request-response.

[0086] As described above, generation of a session identifier and a callback endpoint, and processing of a callback message are executed for managing interactions with the at least one recipient. Thereby, asynchronous control flow is provided and consistency of privacytechnique across multi-steps is maintained.

[0087] In some non-limiting embodiments corresponding to claim 5, the secure communication interface is implemented on at least one of a Near-Real -Time RAN Intelligent Controller (Near-RT RIC), a Sendee Management and Orchestration (SMO) platform, or an O-RAN Cloud (O-Cloud) platform.

[0088] As described above, implementation of the secure communication interface on the Near-RT RIC, the SMO platform, or the O-Cloud platform is executed based on deployment needs.

[0089] In some non-limiting embodiments, the privacy-preserving technique is homomorphic encryption, the transforming comprises encrypting the input data with a homomorphic encryption technique. Encrypting the input data prior to transmission and computation enables recipients to perform permitted operations over ciphertext without access to plaintext, thereby preserving confidentiality while maintaining computational utility.

[0090] In some non-limiting embodiments, the privacy-preserving technique is a differential privacy technique, and the transforming comprises adding calibrated noise to numerical elements of the input data based on a predefined privacy budget. Configuring the predefined privacy budget bounds privacy loss while retaining task-relevant signal, thereby providing quantifiable protections against re-identification.

[0091] In some non-limiting embodiments, the privacy -preserving technique is a Secure MultiParty Computing (SMPC) technique, and the transforming comprises splitting the input data into a plurality of secret shares for transmission to a plurality of recipients. Secret shares are distributed such that no single recipient can reconstruct the input data. Thereby, risks of compromise of any individual recipient are mitigated.

[0092] As described above, splitting the input data into a plurality of secret shares and transmitting the secret shares to the plurality of recipients are executed in accordance with the SMPC technique.

[0093] In some non-limiting embodiments, the input data, the information related to the privacy-preserving technique, and the information associated with the at least one recipient are received from one or more network functions of O-RAN through the secure communication interface. Accepting inputs directly from O-RAN network functions standardizes integration, thereby reducing custom adapters and lowering integration complexity7across multi-vendor deployments.

[0094] In an embodiment [1], data privacy procedures in O-RAN are provided by (a) receiving, at a secure communication interface communicatively coupled to Open Radio Access Network (O-RAN), input data, an information related to a privacy -preserving technique from a plurality of privacy-preserving techniques, and information associated with at least one recipient, wherein the information related to the privacy-preserving technique comprises a ty pe and a plurality of parameters associated with the privacy -preserving technique, (b) transforming the input data based on the information related to the privacy -preserving technique, to obtain privacy -preserved output data, and (c) transmitting the privacy-preserved output data to the at least one recipient through the secure communication interface.

[0095] In an embodiment [2], the method as described in embodiments [1] further includes selectively retaining or discarding the input data, based on a policy associated with the privacypreserving technique.

[0096] In an embodiment [3], the method as described in embodiments [1] or [2] further includes generating a session identifier and a callback endpoint for the at least one recipient; and processing a callback message received on the callback endpoint based on the privacypreserving technique.

[0097] In an embodiment [4], the secure communication interface as described in embodiments [1], [2] or [3] is implemented on at least one of a Near-Real-Time RAN Intelligent Controller (Near-RT RIC), a Service Management and Orchestration (SMO) platform, or an O-RAN Cloud (O-Cloud) platform.

[0098] In an embodiment [5], the input data, the information related to the privacy-preserving technique, and the information associated with the at least one recipient as described in embodiments [1], [2], [3] or [4] are received from one or more network functions of O-RAN through the secure communication interface.

[0099] In an embodiment [6], the privacy-preserving technique as described in embodiments [1], [2], [3], [4] or [5] is federated learning and the transforming comprises (a) transmitting the input data associated with a plurality of recipients to a federated learning server for performing training on the input data and generating a plurality of partial Machine-Learning (ML) models, and (b) transmitting an aggregated ML model, that is generated based on the plurality of partial ML models, to the plurality of recipients.

[0100] In an embodiment [7], the privacy-preserving technique as described in embodiments [1], [2], [3], [4] or [5] is homomorphic encryption, the transforming comprises encrypting the input data w ith a homomorphic encryption technique.

[0101] In an embodiment [8], the privacy-preserving technique as described in embodiments [1], [2], [3], [4] or [5] is a differential privacy technique, and the transforming comprises adding calibrated noise to numerical elements of the input data based on a predefined privacy budget.

[0102] In an embodiment [9], the privacy-preserving technique as described in embodiments [1], [2], [3], [4] or [5] is a Secure Multi-Party7Computing (SMPC) technique and the transforming comprises splitting the input data into a plurality of secret shares for transmission to a plurality of recipients.

[0103] It will be understood by those within the art that, in general, terms used herein, and are generally intended as "open" terms (e.g.. the term "including" should be interpreted as ■‘including but not limited to,” the term “having” should be interpreted as “having at least,” the term “includes” should be interpreted as “includes but is not limited to,” etc.). For example, as an aid to understanding, the detail description may contain usage of the introductory7phrases “at least one” and “one or more” to introduce recitations. However, the use of such phrases should not be construed to imply that the introduction of a recitation by the indefinite articles “a” or “an” limits any particular part of description containing such introduced recitation to inventions containing only one such recitation, even when the introductory7phrases “one or more” or “at least one” and indefinite articles such as “a” or “an” (e.g., “a” and / or “an” should typically be interpreted to mean “at least one” or “one or more”) are included in the recitations; the same holds true for the use of definite articles used to introduce such recitations.

[0104] In addition, even if a specific part of the introduced description recitation is explicitly recited, those skilled in the art will recognize that such recitation should typically be interpreted to mean at least the recited number (e.g., the bare recitation of “two recitations,’’ without other modifiers, typically means at least two recitations, or two or more recitations).

[0105] While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following detailed description.

Claims

We Claim:

1. A method comprising:receiving, at a secure communication interface communicatively coupled to Open Radio Access Network (O-RAN), input data, an information related to a privacy-preserving technique from a plurality7of privacy-preserving techniques, and information associated with at least one recipient, wherein the information related to the privacy-preserving technique comprises a type and a plurality of parameters associated with the privacy-preserving technique;transforming the input data based on the information related to the privacy -preserving technique, to obtain privacy -preserved output data; andtransmitting the privacy -preserved output data to the at least one recipient through the secure communication interface.

2. The method as claimed in claim 1, further comprising selectively retaining or discarding the input data, based on a policy associated with the privacy -preserving technique.

3. The method as claimed in claim 1, wherein the privacy-preserving technique is federated learning and the transforming comprising:transmitting the input data associated with a plurality7of recipients to a federated learning server for performing training on the input data and generate a plurality of partial Machine-Learning (ML) models; andtransmitting an aggregated ML model, that is generated based on the plurality7of partial ML models, to the plurality7of recipients.

4. The method as claimed in claim 1. further comprising:generating a session identifier and a callback endpoint for the at least one recipient; and processing a callback message received on the callback endpoint based on the privacypreserving technique.

5. The method as claimed in claim 1, wherein the secure communication interface is implemented on at least one of a Near-Real-Time RAN Intelligent Controller (Near-RT RIC), a Service Management and Orchestration (SMO) platform or an O-RAN Cloud (O- Cloud) platform.

6. The method as claimed in claim I. wherein the privacy-preserving technique is homomorphic encryption, and the transforming comprising encrypting the input data with a homomorphic encryption technique.

7. The method as claimed in claim 1, wherein the privacy -preserving technique is differential privacy technique, and the transforming comprising adding calibrated noise to numerical elements of the input data based on a predefined privacy budget.

8. The method as claimed in claim 1, wherein the privacy-preserving technique is a Secure Multi-Party Computing (SMPC) technique and the transforming comprising splitting the input data into a plurality of secret shares to a plurality of recipients.

9. The method as claimed in claim 1, wherein the input data, the information related to the privacy-preserving technique, and the information associated with at least one recipient are received from one or more network functions of O-RAN.

10. An apparatus configured to:receive, at a secure communication interface communicatively coupled to Open Radio Access Network (O-RAN), input data, an information related to a privacy -preserving technique from a plurality of privacy-preserving techniques, and information associated with at least one recipient, wherein the information related to the privacy-preserving technique comprises a type and a plurality of parameters associated with the privacypreserving technique;transform the input data based on the information related to the privacy-preserving technique, to obtain privacy-preserved output data; andtransmit the privacy-preserved output data to the at least one recipient through the secure communication interface.

11. The apparatus as claimed in claim 10, wherein the input data is selectively retained or discarded, based on a policy associated with the privacy -preserving technique.

12. The apparatus as claimed in claim 10, wherein the privacy-preserving technique is federated learning and to transform the input data, the apparatus is configured to:transmit the input data associated with a plurality of recipients to a federated learning server for performing training on the input data and generate a plurality of partial Machine- Learning (ML) models; andtransmit an aggregated ML model, that is generated based on the plurality of partial ML models, to the plurality of recipients.

13. The apparatus as claimed in claim 10, wherein the apparatus is further configured to: generate a session identifier and a callback endpoint for the at least one recipient; and process a callback message received on the callback endpoint based on the privacypreserving technique.

14. The apparatus as claimed in claim 10, wherein the secure communication interface is implemented on at least one of a Near-Real-Time RAN Intelligent Controller (Near-RT RIC), a Service Management and Orchestration (SMO) platform or an O-RAN Cloud (O- Cloud) platform.

15. The apparatus as claimed in claim 10, wherein the privacy -preserving technique is homomorphic encr ption, and the transforming comprises encrypting the input data with a homomorphic encryption technique.

16. The apparatus as claimed in claim 10, wherein the privacy-preserving technique is differential privacy technique, and the transforming comprises adding calibrated noise to numerical elements of the input data based on a predefined privacy budget.

17. The apparatus as claimed in claim 10, wherein the privacy-preserving technique is a Secure Multi-Party Computing (SMPC) technique, and the transforming comprises splitting the input data into a plurality’ of secret shares to a plurality of recipients.

18. The apparatus as claimed in claim 10, wherein the input data, the information related to the privacy-preserving technique, and the information associated with at least one recipient are received from one or more network functions of O-RAN.

19. A non-transitory computer readable medium including instructions for performing operations comprising:receiving, at a secure communication interface communicatively coupled to Open Radio Access Network (O-RAN). input data, an information related to a privacy-preserving technique from a plurality of privacy-preserving techniques, and information associated with at least one recipient, wherein the information related to the privacy-preserving technique comprises a type and a plurality of parameters associated wi th the privacy -preserving technique;transforming the input data based on the information related to the privacy-preserving technique, to obtain privacy -preserved output data; andtransmitting the privacy-preserved output data to the at least one recipient through the secure communication interface.

20. The non-transitory computer readable medium as claimed in claim 19, wherein the operations further comprise selectively retaining or discarding the input data, based on a policy associated with the privacy-preserving technique.

Images