Method and apparatus for a vehicle safety behavior layer

By introducing a security layer based on behavior analysis in a remote keyless system, using AI models to distinguish legitimate users and intruders, the problem of insufficient password security in the prior art is solved, and the security and authentication accuracy of vehicles are significantly improved.

CN118985012APending Publication Date: 2024-11-19HARMAN INT IND INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202280095027.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2022-03-01
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing remote keyless system has insufficient security level when facing password attacks, which is easy to be exploited by intruders, and conventional password security systems are difficult to effectively defend against complex attack methods.

Method used

The safety layer based on behavior analysis is adopted, and the trained artificial intelligence model is used to analyze user behavior, distinguish legitimate users from intruders, and perform corresponding actions when abnormal behavior is identified to enhance the safety of the vehicle.

Benefits of technology

Through the behavioral analysis security layer, the security of the remote keyless system is improved, effectively preventing intruders from accessing the vehicle, and enhancing the overall security of the vehicle and the accuracy of user identity verification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118985012A_ABST
    Figure CN118985012A_ABST
Patent Text Reader

Abstract

Methods and systems are described for a behavioral security layer for a remote keyless system of a vehicle, such as a remote keyless entry (RKE) system or a remote keyless ignition (RKI) system. An embodiment of the method may include processing a transmission for operation of the remote keyless system of the vehicle; determining, using the behavioral security layer, whether the transmission is associated with a behavior of a legitimate user of the vehicle; and performing an action based on a determination that the transmission is not associated with a behavior of a legitimate user of the vehicle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to a behavioral security layer for a remote keyless system for a vehicle, such as a remote keyless entry system and a remote keyless ignition system. Background Art

[0002] Embedded systems of some modern vehicles may be connected to various decentralized services, such as multimedia servers, voice command and speech recognition servers, positioning and global navigation satellite system (GNSS) servers (such as global positioning system (GPS) servers), etc. The network security of electronic control units (ECUs) handling sensitive vehicle components (e.g., brakes, engine, etc.) may be compromised through such connections. One method for improving the security of vehicle ECUs includes protecting the integrity of the vehicle interior, for example, ensuring that an intruder does not have physical access to potential attack vectors (such as multimedia radio systems). Therefore, it is desirable that related technologies involved in opening and / or closing a vehicle include adequate security features.

[0003] A remote keyless system may include a remote keyless entry (RKE) system and / or a remote keyless ignition (RKI) system. The RKE system is the successor to the traditional method of opening a car door by inserting a physical key. A key with RKE capability allows the key holder to remotely lock and unlock the car doors, and / or deactivate or activate (e.g., turn off or on) the anti-theft alarm. The RKI system may allow the key holder to remotely start or stop the vehicle's engine. In various embodiments, a remote keyless system may include both RKE and RKI system capabilities.

[0004] A remote keyless system may include two units that are used together to access a vehicle. The first unit, a customer identification device (CID), may be a handheld device carried by a user. For example, the CID may be a key fob. The second unit may be a receiver located inside the vehicle. Communication between the vehicle receiver and the CID may be established via a radio frequency (RF) or infrared (IR) link.

[0005] Remote keyless systems need to be protected to protect digital infrastructure. For example, when the remote keyless system includes an RKE system, if the remote keyless system is compromised, the vehicle-mounted components may be directly exposed to intruders. Some embodiments of conventional security systems for protecting remote keyless systems may include a password-based security system for digital wireless entry into the vehicle, which may have multiple password layers. Cryptographic methods may include fixed code technology, rolling code technology, and challenge-response technology. The above-mentioned security solutions provide a protection mode for the wireless link between the vehicle and the CID. These solutions rely on cryptographic methods to protect the remote keyless system by adopting multiple solutions in both the CID and the vehicle. The security level in a vehicle with a conventional cryptographic security system depends on the strength of the cryptographic identifier (ID) or the key length.

[0006] One measure of the degree of security of a vehicle may be the number of layers in the vehicle security system, such as the number of layers of cryptographic operations in the vehicle security system. Even so, cryptographic operations may be vulnerable to various attacks, including scanning attacks, playback attacks, double thief attacks, challenge forward prediction attacks, and / or dictionary attacks. Another threat to remote keyless systems is the on-board diagnostic (OBD) key programmer. Increasing the number of security layers in the vehicle security system may increase the security level of the vehicle. However, since the methods of cryptographic attacks may already be known, simply layering multiple cryptographic security layers may simply increase the time required for an intruder to access the remote keyless system and enter the vehicle. Summary of the invention

[0007] Disclosed herein are methods and mechanisms for a behavioral security approach that can be used in addition to or in place of a cryptographic security approach to increase the security of a remote keyless system for a vehicle. A behavioral analysis-based security layer can use a trained artificial intelligence (AI) model to analyze the behavior of an individual attempting to access or use a vehicle (e.g., via a remote keyless system) and determine whether the individual is a legitimate user or an intruder. After determining the identity of the individual (e.g., a legitimate user or an intruder), the behavioral analysis-based security layer can perform an action based on whether the individual is determined to be a legitimate user or an intruder.

[0008] The method for the behavioral security layer may include using a trained AI model to process a transmission (e.g., including user behavior) to determine whether the transmission is associated with behavior of a legitimate user, and performing an action based on a determination that the transmission is not associated with behavior of a legitimate user (which may occur in the event of an intrusion). Additionally or alternatively, the method for the behavioral security layer may include receiving a transmission, using a trained AI model to analyze user behavior included in the transmission, and performing an action based on detecting an anomaly in the user behavior during the analysis (e.g., detecting abnormal behavior compared to legitimate user behavior).

[0009] It should be understood that the above summary is provided to introduce a series of concepts further described in the detailed description in a simplified form. It is not meant to identify the key or essential features of the claimed subject matter, the scope of which is uniquely defined by the claims following the detailed description. In addition, the claimed subject matter is not limited to implementations that address any disadvantages described above or in any part of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The present disclosure may be better understood by reading the following description of non-limiting embodiments with reference to the accompanying drawings, in which:

[0011] Figure 1A A schematic diagram showing various layers of a security system for accessing a remote keyless system of a vehicle according to one or more embodiments of the present disclosure;

[0012] Figure 1B A method for accessing a Figure 1A methods for the security system;

[0013] Figure 2 A schematic diagram showing a behavioral safety layer according to one or more embodiments of the present disclosure is shown;

[0014] Figure 3 A method for training according to one or more embodiments of the present disclosure is shown. Figure 2 Methods for AI models of behavioral security layers;

[0015] Figure 4 A method for using a trained AI model of a behavioral safety layer according to one or more embodiments of the present disclosure is shown;

[0016] Figure 5 A method for performing an action based on a determination that a transmission for a remote keyless system is not associated with behavior of a legitimate user is shown in accordance with one or more embodiments of the present disclosure;

[0017] Figure 6 A method for performing an action based on detecting anomalies in the behavior of an individual interacting with a remote keyless system in accordance with one or more embodiments of the present disclosure is shown;

[0018] Figure 7 shows an example partial view of one type of environment for a vehicle according to one or more embodiments of the present disclosure; and

[0019] Figure 8 One or more embodiments of the present disclosure are shown. Figure 7Block diagram of the in-vehicle computing system. DETAILED DESCRIPTION

[0020] Vehicles with remote keyless systems (which may include remote keyless entry and remote keyless ignition capabilities) may have multiple layers of security systems to help prevent intruders from accessing the interior of the vehicle. Figure 1A A schematic diagram of a multi-layered security system for accessing a remote keyless system of a vehicle is shown. The multi-layered security system may include a behavioral security layer, and may also include at least one password security layer. When positioned as a first security layer, the behavioral security layer may process various parameters associated with an attempt to interact with the remote keyless system and perform an action based on identifying the interaction as associated with a legitimate user or associated with an intruder. The action may include allowing the individual attempting to interact with the remote keyless system to access one or more password-based security layers and the remote keyless system, such as Figure 1B shown.

[0021] like Figure 2 As shown, the behavioral security layer includes an AI model for processing transmissions that include parameters associated with user behavior (e.g., user activity data) related to the transmission. Figure 3 The training method shown is used to train the AI ​​model. Figure 4 The method shown uses a behavioral security layer including a trained AI model to identify an individual attempting to interact with a remote keyless system as a legitimate user or an intruder based on user activity data, and perform a corresponding action. The action may be performed based on a determination that a transmission associated with the individual is not associated with the behavior of a legitimate user, such as Figure 5 As shown, or the action may be performed based on detecting anomalies in user behavior, such as Figure 6 shown.

[0022] Figure 7 An example partial view of one type of environment for a vehicle in which a multi-layered safety system including a behavioral safety layer is implemented, and Figure 8 Shows Figure 7 Block diagram of the in-vehicle computing system.

[0023] Therefore, the behavioral security layer uses behavioral analysis to detect intruders entering or attempting to enter the vehicle. The AI ​​model can be trained based on legitimate user activity data collected by the behavioral security layer to identify complex and / or complicated patterns in the behavior of legitimate users of a given vehicle. The parameters of the user activity data can reflect user behavior. Behaviors other than those identified as legitimate user behaviors by the AI ​​model can be considered illegal behaviors, which may indicate that an intruder is attempting to access. For example, an intruder may place a jammer to block the RF communication link, may record communication messages between the vehicle and the CID, may send their own code words to open the vehicle door, etc. However, the behavior of intruders attempting to enter the vehicle by illegal means may exhibit their own operating modes, which may be different from the behavior of legitimate users. Therefore, a trained behavioral AI model can be used to detect intruder behavior, and action can then be taken (e.g., to prevent further access to the remote keyless system).

[0024] For example, a transmission for a remote keyless system may be received by the vehicle, and various parameters associated with the transmission may be analyzed to determine whether the user behavior associated with the transmission is legitimate (e.g., the behavior of a legitimate user) or illegitimate (e.g., the behavior of an intruder). In various embodiments, the transmission may include one or more wireless transmissions that conform to the protocol of the remote keyless system. If the transmission is identified as exhibiting behaviors associated with those of an intruder, the parameters may be recorded (e.g., logged), and the previously identified legitimate user may be alerted of the intruder's entry. In some embodiments, the intruder may be allowed to access further security layers, such as a password security layer, while in other embodiments, the intruder may be prevented from further accessing the remote keyless system. If the transmission is identified as having behaviors associated with those of a legitimate user, the legitimate user may be allowed to access further security layers, such as a password security layer. In this way, adding a behavioral analysis-based security layer that uses an AI model to distinguish between legitimate users and intruders may increase the security of the vehicle's remote keyless system.

[0025] As briefly described above, the behavioral safety layer may be implemented as an additional layer to a vehicle's existing multi-layered safety system. Figure 1A A multi-layer security system 100 is shown, which includes a first layer 110, a second layer 120, a third layer 130, a fourth layer 140, and a fifth layer 150. A core remote keyless system 160 may be protected by each of the first layer 110, the second layer 120, the third layer 130, the fourth layer 140, and the fifth layer 150.

[0026] The behavioral security layer may be implemented as an additional security layer (e.g., layer n) on top of a password (or other type) based security layer (e.g., layer n-1, layer n-2, etc.). For example, in various embodiments, the first layer 110 may be a behavioral security layer, and the second layer 120, the third layer 130, the fourth layer 140, and the fifth layer 150 may be password security layers. Thus, the behavioral analysis layer may be the first security layer accessed by a user who may or may not be a legitimate user.

[0027] In other embodiments, the behavioral security layer can be integrated between security layers (e.g., cryptographic layers or other layers). For example, the first layer 110 can be a cryptographic security layer, the second layer 120 can be a behavioral security layer, and the third layer 130, the fourth layer 140, and the fifth layer 150 can be cryptographic security layers. In various embodiments, there can be any number of layers before and / or after the behavioral security layer, and the number of layers on either side of the behavioral security layer can be equal or unequal.

[0028] In some embodiments, the behavioral security layer can include a single-layer security system. For example, the behavioral security layer can be used independently of the cryptographic layer or other type of security layer of the remote keyless system. For example, the single-layer security system can be used for systems with lower security requirements than the remote keyless system, such as for interior vehicle components. In addition to the multi-layer security system, a single behavioral security layer can also be implemented, such that the multi-layer security system including at least one behavioral security layer and at least one cryptographic security layer or other type of security layer protects the remote keyless system, and the single behavioral security layer protects the interior vehicle components.

[0029] As about Figures 1B to 6 Further describing, the behavioral security layer may be implemented as the first security layer of a multi-layered security system for a vehicle. Figure 1B A high-level method 102 is shown for implementing a behavioral security layer as a first security layer, followed by at least one cryptographic security layer. Figure 1B About Figure 1A Elements that are described as being related are similarly numbered.)

[0030] When a user (who may or may not be a legitimate user) attempts to access a vehicle, such as via a remote keyless system, user activity data 104 may be provided to a behavioral security layer 115 (e.g., first layer 110). User activity data 104 may include various parameters associated with user behavior, such as transmissions associated with attempting keyless entry into a vehicle. Such transmissions may be generated and / or sent by a CID and may be received and / or processed by one or more devices of the vehicle (e.g., a vehicle receiver). The values ​​of the various parameters associated with a given transmission may then establish user behavior for training the behavioral security layer.

[0031] As about Figures 2 to 6 Further describing, the behavioral security layer 115 may include an AI model trained for anomaly detection. The AI ​​model may analyze the user activity data 104 (e.g., by analyzing parameters associated with the user's behavior) and may determine whether the user is a legitimate user or an intruder, for example, based on the detection of abnormal behavior. The behavioral security layer 115 may perform different actions depending on whether the user is identified as a legitimate user or an intruder. Figures 4 to 6 Such actions are further described in detail below. The user may continue to further pass through various password-based security layers 125 (such as layer n-1, layer n-2, etc.), as described in detail below. Figures 4 to 6 The password-based security layer 125 may allow a user to access the remote keyless system 160 , thereby allowing the user to unlock, open, and / or otherwise access the vehicle.

[0032] Figure 2 A high-level flow 200 of a behavioral security layer is shown. As briefly described above, the behavioral security layer includes a trained anomaly detection AI model, such as an AI-based behavioral model 220, which can distinguish between the behavior of a legitimate user 230 (such as the owner and / or operator of the vehicle) and an intruder 240. Once the anomaly detection AI model is trained, it can be used each time a user (who may or may not be a legitimate user) attempts to access the remote keyless system.

[0033] For example, when a user attempts to access a vehicle with a behavioral security layer, user activity data (e.g., user activity data 104) including a plurality of user behavior parameters 210 is sent to the vehicle and input into an AI-based behavior model 220 (e.g., a trained anomaly detection AI model), which analyzes the user activity data to determine whether the user exhibits the behavior of a legitimate user 230 or the behavior of an intruder 240. In various embodiments, vehicle parameters and / or non-vehicle parameters may be considered.

[0034] The various user behavior parameters 210 may include multiple factors used to access and operate the remote keyless system of the vehicle, such as: time of day (e.g., time of day corresponding to the transmission); date of operation (e.g., date of operation corresponding to the transmission); location of the vehicle (e.g., GNSS location); distance between the vehicle and the CID sending the transmission; number of times the CID is operated per day; time taken to open a door of the vehicle; time taken to close a door; force to open a door; force to close a door; temperature inside the vehicle; temperature outside the vehicle; and humidity. These parameters describe the behavior of a user operating the remote keyless system. These parameters are used to quantify modeling of legitimate user behavior. Various numbers of user behavior parameters 210 may be used to determine whether a user exhibits the behavior of a legitimate user or the behavior of an intruder. For example, at least a predetermined number of the user behavior parameters listed above may be used, or all of the user behavior parameters listed above may be used. In various embodiments, the user behavior parameters used may include other parameters in addition to those listed above. About Figures 3 to 6 Describes more details about collecting user activity data including user behavior parameters, selecting and training AI models, and using the trained AI models to identify legitimate users and intruders based on user behavior.

[0035] Figure 3 A method for training an AI model for a behavioral security layer is shown. In various embodiments, the AI ​​model may be substantially similar to the AI-based behavioral model 220. The behavioral security layer may include deep learning-based anomaly detection modeling. The vehicle may collect user activity data and / or generate a data set that is used to train an anomaly detection AI model to learn user behavior and distinguish between the behavior of legitimate users and the behavior of intruders.

[0036] Training of the behavioral security layer may occur during a training period, where user activity data (e.g., including various user behavior parameters) may be collected from the vehicle and CID. The training period may be any duration (e.g., one week, three months, six months, etc.) during which a sufficient amount of user activity data is collected. A sufficient amount of data may be an amount of data from which anomalies in user behavior (e.g., abnormal behavior compared to legitimate user behavior) may be detected. If a sufficient amount of data is collected that can be used to train an anomaly detection AI model, data collection may end before the training period is completed. In another embodiment, user activity data for a predetermined number of access attempts (e.g., fifty uses of a remote keyless system, three hundred uses of a remote keyless system, or one thousand uses of a remote keyless system) may be collected. For such embodiments, the predetermined number of access attempts may be configurable.

[0037] During the training period, each time the remote keyless system is used, user activity data can be sent from the CID to the vehicle. For example, a single user or multiple users may attempt to access the remote keyless system using any number of CIDs that can be configured (e.g., configured by the vehicle manufacturer) for use with the vehicle during the training period. The user activity data may include fourteen parameters: thirteen user behavior parameters and an assigned user ID. The user ID may include a digital ID, a user name, or other identification tags. The user ID of each user of the remote keyless system may be different, however, the identity of any particular user may be determined, or the user ID of each CID configured for use with the vehicle may be different. In some embodiments, the user ID may be derived from a vehicle system other than the remote keyless system and / or for a vehicle system other than the remote keyless system. Therefore, for some embodiments, the user ID may be based on biometrics or other user activities (e.g., from a pre-existing mechanism for identifying individual users). Additionally or alternatively, in some embodiments, the user ID of each CID may be different, such as when the vehicle can be accessed by multiple CIDs, each CID belongs to a different user.

[0038] The user activity data (eg, user behavior parameters and user ID) collected during the training period may include user behavior parameters 210, such as Figure 2 As shown. The user behavior data may also include additional user behavior parameters and / or alternative user behavior parameters in addition to those listed herein. For each instance of accessing the remote keyless system, the aforementioned user activity data may be collected, including the user behavior parameters and the user ID. Each time the remote keyless system is used, a different user ID and set of user behavior parameters may be recorded. A data set may be generated from all user activity data collected during the training period.

[0039] Training of the AI ​​model may implicitly include combining user behavior parameters associated with multiple user IDs. The data set generated during the training period may accordingly combine user behavior parameters corresponding to multiple user IDs, which may correspond to one or more legitimate users and / or one or more CIDs.

[0040] A new set of user behavior parameters may be generated each time the remote keyless system is used, resulting in hundreds of different user activity data sets being generated during the training period. For a vehicle with two users, at the end of the training period, the trained model may identify user activity data (including user behavior parameters and user IDs) associated with one or more legitimate users and / or one or more CIDs as legitimate.

[0041] like Figure 3As shown in part 302 of , each of the user behavior parameters in the user activity data set can become a user activity feature of the data set. For example, user activity feature 1 can be the time of day, user activity feature 2 can be the date when the remote keyless system is operated, user activity feature 3 can be the GNSS position of the vehicle, and so on up to n user activity features. The data set can then include a series of data points for each user activity feature. Therefore, the data set can include a series of values ​​for the user activity feature set corresponding to the user behavior parameter set respectively. In various embodiments, the user activity features can be statistically analyzed to identify patterns and / or changes associated with the data set.

[0042] At section 304, in some embodiments, a user activity feature set (e.g., user activity feature 1, user activity feature 2, etc.) may be selected and feature engineering may be performed. Feature engineering may include converting features of the user activity feature set from raw data to data that may be more suitable for training an AI model. In some embodiments, existing user activity features may be converted (e.g., by scaling). For some embodiments, new features may be created based on existing user activity features (e.g., by combining user activity features). In some embodiments, some user activity features may be removed from the user activity feature set. In other words, feature engineering may facilitate tuning of user activity features for training an AI model.

[0043] After feature engineering, an anomaly detection neural network (e.g., an AI model) may be selected based on the available data. For example, an anomaly detection neural network may be selected based on the user activity features of the user activity feature set. If the number of features that are likely to have a sufficient number of data points is less than a threshold number of features, then the first anomaly detection neural network may be selected instead of the second anomaly detection neural network. The threshold number of features may be thirteen features, as described above in Figure 2 When thirteen features are identified, an autoencoder artificial neural network can be selected as the AI ​​model. For different implementations, other models can be selected based on available data.

[0044] At section 306, the feature-engineered user activity feature set is encoded. For example, it may be determined that the user activity feature set represents behavior associated with a legitimate user, and thus the user activity feature set may be further converted into a form that is more usable by an AI model.

[0045] At portion 308, hyperparameters that can be used to train the selected AI model can be selected. The selected hyperparameters can correspond to the selected AI model and can be used to control the training of the selected model. The hyperparameters can include the amount of data, batch size, learning rate, etc. Initially, the values ​​of the hyperparameters can be randomly selected. For each implementation of the behavior analysis model (e.g., in a different vehicle), the number and type of hyperparameters can be fixed. In various embodiments, portion 306 can occur before or after portion 308.

[0046] At section 310, the encoded feature set and the selected hyperparameters may be input into the selected AI model for anomaly detection to train the AI ​​model. Training may include tuning the parameters of the AI ​​model, as shown at section 312, to train the AI ​​model to correctly identify legitimate users based on user activity data (e.g., user behavior parameters). For example, adjusting the AI ​​model parameters may include increasing or decreasing at least one weight and / or bias of the AI ​​model. Thus, the behavioral security layer may be trained by adjusting the AI ​​model parameters until a minimum error is reached. In some embodiments, the minimum error may be 5% (e.g., 5% of legitimate users are identified as intruders, and vice versa) or 10%, or another suitable value.

[0047] Once the minimum error is achieved, the hyperparameters may be tuned and / or adjusted to select a set of hyperparameters for the AI ​​model so that the behavioral safety layer can operate with an error as close to the minimum error as possible. For example, the number and type of hyperparameters may be fixed in the implementation of the behavioral safety layer in different vehicles. The weights and biases of each AI model may vary from vehicle to vehicle because the AI ​​model may be trained independently based on the user of each vehicle.

[0048] At section 314, a trained AI model for anomaly detection (herein referred to as an AI model) may thus be prepared to detect abnormal behavior in user activity data using a remote keyless system in a corresponding vehicle. In some embodiments, since the user behavior parameters may include personal data, the training of the AI ​​model may be performed on the vehicle itself for privacy reasons. For some embodiments, the training of the AI ​​model may be performed on a cloud network communicatively connected to the vehicle.

[0049] Figure 4 A method 400 for using a trained AI model of a behavioral security layer is shown. The AI ​​model can be based on Figure 3 Method 400 may be implemented after a training period in which a dataset of legitimate user activity data is generated.

[0050] At section 402, user activity data is collected in real time when a user who may or may not be a legitimate user attempts to access a remote keyless system of a vehicle. The user activity data may include user behavior parameters (including user ID), such as Figures 2 to 3 A selection of user behavior parameters such as those described above may be collected. In some embodiments, the selection may include parameters substantially similar to those of user behavior parameters 210, such as those described above with respect to Figure 2 Alternatively, at least a predetermined number of user behavior parameters 210 may be collected, as discussed above.

[0051] At section 404, the collected user activity data may be processed, which may include feature engineering and / or data encoding. Figure 3 The feature engineering and data encoding of the collected user activity data are performed in a similar manner as the feature engineering and data encoding of the user activity features described in the foregoing description. Thus, the collected user activity data can be converted from raw data to data that can be used by a trained AI model to detect abnormal behavior.

[0052] At section 406, hyperparameters may be imported for use with the AI ​​model for anomaly detection. For example, hyperparameters determined during AI model training (e.g., such as those regarding Figure 3 Importing these hyperparameters for use with collected user activity data can help determine whether the collected user activity data is associated with legitimate user behavior or with intruder behavior.

[0053] At portion 408, a trained AI model is imported to detect anomalous behavior in the collected user features. As discussed herein, an anomaly may correspond to a user activity data set that the AI ​​model identifies as sufficiently different from the user activity data of a legitimate user or that is not identified as similar to the user activity data of a legitimate user (or both). Thus, an anomaly may represent user behavior that does not fall within the complex and / or complicated behavior patterns that the model AI has been trained to learn. For example, if the force used to open a vehicle door is different from the force that a legitimate user would tend to use, or if the time of day at which the vehicle was attempted to be opened is different from the time of day at which a legitimate user would attempt to open the vehicle, the trained AI model may identify the corresponding user activity data set as different from the user activity data of a legitimate user. About Figures 5 and 6 Describes more details about using AI models for anomaly detection to analyze the collected user activity data.

[0054] At section 408, the trained AI model for anomaly detection may determine whether the user exhibits the behavior of a legitimate user 410 or the behavior of an intruder 412 based on the collected user activity data (e.g., from section 402). Figures 5 and 6 Further described, actions may be taken based on the determined identity of the user. If the user exhibits behavior of an intruder, the method 400 may proceed to section 414. If the user exhibits behavior of a legitimate user, the method 400 may proceed to section 416.

[0055] At section 416, if the user is identified as a legitimate user, the multi-layer security system may proceed from layer n (e.g., behavioral security layer) of remote keyless system security toward layer n-1, layer n-2, etc. of remote keyless system security, which in various embodiments may include one or more password security layers. At section 418, after any password security layer, the user may access the remote keyless system.

[0056] At section 414, if the user is determined to be an intruder, an event log may be recorded and / or a notification may be sent to one or more legitimate users (eg, whose data is used to identify the intruder). Figure 3 As previously discussed, the behavioral security layer may include data corresponding to multiple users accessing the remote keyless system (e.g., when the vehicle has multiple owners and / or operators), and thus multiple users may be classified as legitimate users during training. At portion 416, a user determined to be an intruder may be allowed to access the cryptographic security layer, and at portion 418, a user determined to be an intruder may be allowed to access the remote keyless system.

[0057] In various embodiments, there may be some errors (e.g., a 5% false determination rate, or another rate) involving the AI ​​model's determination of whether a user is a legitimate user or an intruder. Thus, in embodiments where the AI ​​model incorrectly determines that a legitimate user is an intruder, the legitimate user may still be able to access the vehicle using other layers of cryptographic security.

[0058] In various embodiments, new user behaviors may be added to the data set before or after the training period. For example, in some embodiments, the data set of the behavioral security layer may be transferred from a first vehicle to a second vehicle (e.g., a newly acquired vehicle of a legitimate user) before the training period is completed in the second vehicle. Alternatively or additionally, a user who might otherwise be identified as an intruder may be added as a legitimate user after obtaining approval from an existing legitimate user.

[0059] In one embodiment of multiple embodiments, using a behavioral analysis security layer to distinguish between legitimate users and intruders can be described as a method for determining whether user behavior is associated with behavior of a legitimate user. In other words, the method can include comparing the user behavior with behavior previously identified as behavior of a legitimate user and attempting to identify whether there is sufficient behavioral similarity.

[0060] Figure 5 A method 500 is shown for performing an action based on a determination that a transmission (e.g., from a CID) for a remote keyless system for a vehicle is not associated with the behavior of a legitimate user of the vehicle. The method 500 may be applied to a vehicle having a multi-layer security system that includes a behavioral security layer. When a user who may or may not be a legitimate user attempts to access the vehicle, such as by pressing a button on a CID (e.g., a key fob) or approaching the vehicle, a transmission may be sent to the vehicle. The transmission may be received by the vehicle via one of: an RF-based link; or an IR-based link.

[0061] At portion 502, method 500 includes processing a transmission for an operation of a remote keyless system with a behavioral security layer. In some embodiments, the operation may be selected from the group consisting of: a door lock operation; a door unlock operation; an engine start operation; an engine stop operation; an anti-theft alarm activation operation; an anti-theft alarm deactivation operation; and a panic-signal operation.

[0062] As described above, the remote keyless system can be implemented in a vehicle and can include at least one of the RKE and RKI system capabilities. The embodiment of the remote keyless system may include a passive keyless (PK) system, which includes a passive keyless entry (PKE) system, a passive keyless start (PKS) system, and a passive keyless entry and start (PKES) system. The PKES system can enable a user to unlock and start the vehicle by carrying a CID in his pocket. Typically, the PKES system can use a security protocol based on a challenge-response between a vehicle and a CID, wherein the vehicle periodically scans the CID to determine its proximity. When the CID confirms that it is close, the vehicle sends a challenge together with its ID and waits for the response of the CID. After the true response from the CID, the vehicle unlocks itself.

[0063] The behavioral security layer may include an AI model as discussed herein, such as an anomaly detection neural network. In one embodiment of the various embodiments, the Figure 3 Thus, one or more user behavior parameters (e.g., about Figures 2 to 3The transmissions processed by method 500 may include one or more user behavior parameters of the kind used to train the AI ​​model. For example, the transmission may include the time of day of the transmission, the date of the transmission, the location of the vehicle, the distance between the vehicle and the CID sending the transmission, the number of times the CID is operated per day, the time it takes to open a door of the vehicle, the time it takes to close the door, the force to open the door, the force to close the door, the temperature inside the vehicle, the temperature and / or humidity outside the vehicle.

[0064] At section 504, method 500 includes using a behavioral security layer to determine whether the transmission is associated with the behavior of a legitimate user of the vehicle. For example, the user behavior parameters of the transmission may be analyzed by an AI model that has been trained to learn patterns of user behavior parameters associated with legitimate users. Determining whether the transmission is associated with the behavior of a legitimate user may include comparing the user behavior parameters of the transmission with a data set of learned patterns. For example, the transmission may include the distance between the vehicle and the CID that sent the transmission. If the distance is different from the distance that the AI ​​model associates it with the transmission of a legitimate user, the AI ​​model may identify the transmission as not associated with the behavior of the legitimate user. In one embodiment of multiple embodiments, the transmission may include all of the aforementioned user behavior parameters. If a user behavior parameter greater than a threshold number (e.g., half of the user behavior parameters) is determined to be not associated with the behavior of a legitimate user, the AI ​​model may identify the user as an intruder.

[0065] At portion 506 of method 500, if it is determined that the transmission is not associated with the behavior of a legitimate user of the vehicle, method 500 may proceed to portion 508, and if it is determined that the transmission is associated with the behavior of a legitimate user of the vehicle, method 500 may proceed to portion 510. At portion 508, method 500 may include performing an action. The action may include generating an alert regarding the transmission and / or refraining from performing an action. For example, the alert may be a notification sent to a smartphone or other device of one or more legitimate users of the vehicle.

[0066] As mentioned above Figure 1A to Figure 2 , Figure 4 As described in , the behavioral security layer can be one of multiple security layers of the remote keyless system. Multiple security layers may also include one or more password security layers. In some embodiments, a user who has been identified as an intruder by the AI ​​model may be able to access another security layer and attempt to access the vehicle. Therefore, a legitimate user who may have been mistakenly identified as an intruder by the behavioral analysis security layer may still be able to access the remote keyless system. Alternatively, for some embodiments, a user who has been identified as an intruder by the AI ​​model may be restricted from accessing another security layer (e.g., a password security layer) of the remote keyless system.

[0067] At portion 510, method 500 includes processing a transmission for operation of a remote keyless system using a remaining security layer in the plurality of security layers. When the plurality of security layers include one or more cryptographic security layers, the one or more cryptographic security layers may be used to determine whether the transmission is legitimate after determining whether the transmission is associated with behavior of a legitimate user. For example, the one or more cryptographic security layers may analyze a code sent by a user for accessing a vehicle, as described above (rather than being analyzed by an AI model for analyzing user behavior).

[0068] As discussed above, method 500 performs an action (e.g., generates an alert and / or refrains from performing an operation) based on a determination that a transmission from the CID is not associated with the behavior of a legitimate user of the vehicle. Additionally or alternatively, a trained AI model of a behavioral security layer may be used in a method in which an action is performed based on the AI ​​model's identification of anomalous behavior in user activity data. For example, as discussed below, an action may be performed when a difference is identified rather than when a lack of similarity is identified.

[0069] Figure 6 A method 600 for performing an action based on detecting anomalies in the behavior of an individual interacting with a remote keyless system is shown. In method 600, a behavioral analysis model can be used to detect abnormal behavior in user activity data and thus distinguish between legitimate users and intruders. When abnormal behavior is detected, the user can be identified as an intruder and the method can perform a corresponding action.

[0070] At section 602, when a user attempts to access the vehicle, such as by pressing a button on a CID (e.g., a key fob) or approaching the vehicle, the vehicle may receive a transmission to access functionality of a remote keyless system of the vehicle. The functionality of the remote keyless system may include locking one or more doors, unlocking one or more doors, starting the engine, stopping the engine, activating the anti-theft alarm, deactivating the anti-theft alarm, and / or operating a panic signal.

[0071] As described above, the remote keyless system may include multiple security layers, one of which is a behavioral security layer. At portion 604, method 600 may include using a behavioral analysis model (e.g., a behavioral security layer as discussed herein) to analyze a behavior corresponding to a transmission. For example, the behavioral analysis model may be an AI model, such as an anomaly detection neural network. The behavioral analysis model may be trained using one or more parameters associated with a behavior corresponding to a transmission accessing a function of the remote keyless system (e.g., a behavioral security layer as discussed herein). Figure 3For example, one or more parameters may include the time of day of the transmission, the date of the transmission, the location of the vehicle, the distance between the vehicle and the CID sending the transmission, the number of times the CID is operated per day, the time taken to open the door of the vehicle, the time taken to close the door, the force to open the door, the force to close the door, the temperature inside the vehicle, the temperature and / or humidity outside the vehicle. These parameters may reflect user behavior in a complex and / or complicated manner, which may be different for a legitimate user than for an intruder. The transmission may include all or a selection of the foregoing parameters. The behavioral analysis model may analyze all parameters corresponding to the received transmission or analyze a selection of the data.

[0072] Thus, analyzing user behavior may include performing anomaly detection analysis on all parameters or selections of parameters corresponding to received transmissions. For example, an anomaly may be that the force to open a door is different than the force to open a door that the AI ​​model associates with transmissions from a legitimate user (e.g., learned by the behavioral analysis model to associate with legitimate user behavior).

[0073] At section 606, if no anomalies are detected in the behavior analysis, method 600 may proceed to section 608, and if an anomaly is detected in the behavior analysis, method 600 may proceed to section 610. At section 608, method 600 may include analyzing the behavior (e.g., all or a selection of behaviors corresponding to the transmission) using a cryptographic security layer. One or more cryptographic security layers may be used to determine whether the transmission is legitimate after determining whether the transmission includes one or more anomalies. For example, one or more cryptographic security layers may analyze a code sent by a user to access a vehicle, as described above (rather than being analyzed by an AI model used to analyze user behavior).

[0074] At portion 610, method 600 may include performing an action. The action may include generating an alert regarding the transmission and / or refraining from performing the function. For example, the alert may be a notification sent to a smartphone or other device of a legitimate user coupled to the vehicle.

[0075] As mentioned above Figure 1A to Figure 2 , Figure 4 As described in , the behavioral security layer can be one of multiple security layers of the remote keyless system. Multiple security layers may also include one or more password security layers. In some embodiments, a user who has been identified as an intruder by the AI ​​model may be able to access another security layer and attempt to access the vehicle. Therefore, a legitimate user who may have been mistakenly identified as an intruder by the behavioral analysis security layer may still be able to access the remote keyless system. Alternatively, for some embodiments, a user who has been identified as an intruder by the AI ​​model may be restricted from accessing another security layer (e.g., a password security layer) of the remote keyless system.

[0076] The behavioral security layer may be implemented in an embedded system of the vehicle, which may include a remote keyless system ECU. Additionally or alternatively, the embedded system may include a processor with a digital cockpit ECU, a body control ECU, etc., where the flash firmware contains a security method based on behavioral analysis. Figures 7 and 8 Describes further details regarding vehicle systems in which a behavioral safety layer may be implemented.

[0077] The transmission of the remote keyless system may be unidirectional, where the transmission direction is from the CID to the vehicle. When a button on the CID is pressed, the CID may send a function code for the corresponding function of the remote keyless system (e.g., to unlock the door), depending on which button is pressed. After receiving the function code, the receiver may command the hardware of the remote keyless system (e.g., in the vehicle) to take appropriate action. Some of the remote access functions may include vehicle locking, vehicle unlocking, remote engine start, and / or activation of an emergency signal (as well as other remote access functions disclosed herein). Therefore, a vehicle with a remote keyless system can be remotely opened by pressing a button on the CID or even without a CID, rather than inserting a physical key.

[0078] Figure 7 An exemplary partial view of one type of environment (the interior of a cabin 700 of a vehicle 702 in which a driver and / or one or more passengers may be seated) for a safety system including a behavioral safety layer as disclosed herein is shown. Figure 7 The vehicle 702 may be a motor vehicle including a drive wheel (not shown) and an internal combustion engine 704. The internal combustion engine 704 may include one or more combustion chambers that may receive intake air via an intake passage and exhaust combustion gases via an exhaust passage. The vehicle 702 may be a road car as well as other types of vehicles. In some examples, the vehicle 702 may include a hybrid propulsion system that includes an energy conversion device that is operable to absorb energy from vehicle motion and / or the engine and convert the absorbed energy into an energy form suitable for storage by an energy storage device. The vehicle 702 may include an all-electric vehicle that incorporates a fuel cell, a solar energy capture element, and / or other energy storage system for powering the vehicle.

[0079] As shown, the dashboard 706 may include various displays and controls accessible to a human driver (also referred to as a user) of the vehicle 702. For example, the dashboard 706 may include a touch screen 708 of an onboard computing system 709 (e.g., an infotainment system) and an instrument cluster 710. The onboard computing system 709 may include elements of a remote keyless system and / or a security system including a behavioral security layer (as disclosed herein). The touch screen 708 may receive user input to the onboard computing system 709 to control elements of a remote keyless system and / or a security system including a behavioral security layer, audio output, visual display output, user preferences, control parameter selection, etc. In some embodiments, one or more hardware elements of the onboard computing system 709 (such as a touch screen 708, a display screen 711, various control dials, knobs and buttons, memory, a processor, and any interface elements (e.g., a connector or port)) may form an integrated host unit installed in the dashboard 706 of the vehicle. The host unit may be fixedly or removably attached to the dashboard 706. In additional or alternative embodiments, one or more hardware elements of the onboard computing system 709 may be modular and installable at multiple locations in the vehicle.

[0080] The cabin 700 may include one or more sensors for monitoring the vehicle, the user, and / or the environment. For example, the cabin 700 may include: one or more seat-mounted pressure sensors configured to measure pressure applied to the seat to determine the presence of a user; a door sensor configured to monitor door activity; a humidity sensor for measuring the moisture content of the cabin; a microphone for receiving user input in the form of a voice command to enable the user to make a phone call and / or measure ambient noise in the cabin 700, etc. It should be understood that the above sensors and / or one or more additional or alternative sensors may be positioned in any suitable location of the vehicle. For example, the sensor may be positioned in the engine compartment, on an exterior surface of the vehicle, and / or in other suitable locations for providing information about the operation of the vehicle, the environmental conditions of the vehicle, the user of the vehicle, etc. Information about the environmental conditions of the vehicle, the vehicle state, or the driver of the vehicle may also be received from sensors that are external to the vehicle / separate from the vehicle (i.e., not part of the vehicle system), such as sensors coupled to the external device 750 and / or the mobile device 728.

[0081] The vehicle compartment 700 may also include one or more user objects, such as a mobile device 728, stored in the vehicle before, during, and / or after travel. The mobile device 728 may include a smart phone, a tablet computer, a laptop computer, a portable media player, and / or any suitable mobile computing device. The mobile device 728 may be connected to the onboard computing system via a communication link 730. The communication link 730 may be wired (e.g., via a universal serial bus (USB), a mobile high-definition link (MHL), a high-definition multimedia interface (HDMI), Ethernet, etc.) or wireless (e.g., via Bluetooth®, Wi-Fi®, Wi-Fi Direct®, near field communication (NFC), a cellular connection, etc.), and is configured to provide two-way communication between the mobile device and the onboard computing system. (Bluetooth® is a registered trademark of Bluetooth SIG, Inc., Kirkland, WA. Wi-Fi® and Wi-Fi Direct® are registered trademarks of the Wi-Fi Alliance, Austin, Texas.) The mobile device 728 may include one or more wireless communication interfaces for connecting to one or more communication links (e.g., one or more of the example communication links described above). The wireless communication interface may include: one or more physical devices, such as antennas or ports, that are coupled to data lines to carry data sent or received; and one or more modules / drivers that are used to operate the physical devices based on other devices in the mobile device. For example, the communication link 730 can provide sensor signals and / or control signals from various vehicle systems (such as a vehicle audio system, climate control system, etc.) and the touch screen 708 to the mobile device 728, and can provide control signals and / or display signals from the mobile device 728 to the vehicle systems and touch screen 708. The communication link 730 may also provide power from the onboard power source to the mobile device 728 to charge the mobile device's internal battery.

[0082] The onboard computing system 709 may also be communicatively coupled to additional devices that are operated and / or accessed by a user but are located outside the vehicle 702, such as one or more external devices 750. In the depicted embodiment, the external devices are located outside the vehicle 702, but it will be appreciated that in alternative embodiments, the external devices may be located inside the vehicle compartment 700. The external devices may include a CID, a server computing system, a personal computing system, a portable electronic device, an electronic wristband, an electronic headband, a portable music player, an electronic activity tracking device, a pedometer, a smart watch, a GPS system, etc. The external device 750 may be connected to the onboard computing system via a communication link 736, which may be wired or wireless, as discussed with reference to the communication link 730, and is configured to provide two-way communication between the external device and the onboard computing system. For example, the external device 750 may include one or more sensors, and the communication link 736 may send the sensor output from the external device 750 to the onboard computing system 709 and the touch screen 708. The external device 750 may also store and / or receive information regarding contextual data, user behavior / preferences, operating rules, etc., and may send such information from the external device 750 to the onboard computing system 709 and the touchscreen 708 .

[0083] The onboard computing system 709 may analyze input received from the external device 750, the mobile device 728, and / or other input sources, and select settings for various onboard systems (such as a remote keyless system and / or elements of a security system including a behavioral security layer, or a climate control system, or an audio system), provide output via the touch screen 708 and / or speaker 712, communicate with the mobile device 728 and / or the external device 750, and / or perform other actions based on the assessment. Thus, in various embodiments, the onboard computing system 709 may include various portions of a vehicle receiver for receiving transmissions from a CID, as disclosed herein. In some embodiments, all or a portion of the assessment may be performed by the mobile device 728 and / or the external device 750.

[0084] In some embodiments, one or more of the external devices 750 may be indirectly communicatively coupled to the onboard computing system 709 via the mobile device 728 and / or another of the external devices 750. For example, the communication link 736 may communicatively couple the external device 750 to the mobile device 728 such that output from the external device 750 is relayed to the mobile device 728. Data received from the external device 750 may then be aggregated at the mobile device 728 with data collected by the mobile device 728, with the aggregated data then sent to the onboard computing system 709 and touchscreen 708 via the communication link 730. Similar data aggregation may occur at the server system and then sent to the onboard computing system 709 and touchscreen 708 via the communication link 736 and / or the communication link 730.

[0085] Figure 8 A block diagram of an onboard computing system 709 configured and / or integrated within a vehicle 702 is shown. The onboard computing system 709 may perform one or more of the methods described herein in some embodiments, such as methods 400, 500, and / or 600. In various embodiments, the onboard computing system 709 or other components including the ECU of the vehicle 702 may include one or more processors and non-transitory memory with executable instructions, which when executed may cause one or more processors to perform various parts of methods 400, 500, and / or 600. Therefore, the safety system including the behavioral layer as disclosed herein may be implemented using one or more processors and / or memory of the onboard computing system 709 (or other components including the ECU of the vehicle 702). In some examples, the onboard computing system 709 may be a vehicle infotainment system configured to provide information-based media content (audio and / or visual media content, including the safety system including the behavioral security layer as disclosed herein, entertainment content, navigation services, etc.) to the vehicle user to enhance the operator's in-vehicle experience. The in-vehicle computing system 709 may include or be coupled to various vehicle systems, subsystems, hardware components, and software applications and systems that are or may be integrated into the vehicle 702 to enhance the in-vehicle experience of the driver and / or passengers.

[0086] The vehicle computing system 709 may include one or more processors including an operating system processor 814 and an interface processor 820. The operating system processor 814 may execute an operating system on the vehicle computing system 709 and control input / output, display, playback, and other operations of the vehicle computing system 709. The interface processor 820 may interface with a vehicle control system 830 via an inter-vehicle system communication module 822.

[0087] The inter-vehicle system communication module 822 may output data to one or more other vehicle systems 831 and / or one or more other vehicle control elements 861, while also receiving data input from other vehicle systems 831 and other vehicle control elements 861, for example, through the vehicle control system 830. When outputting data, the inter-vehicle system communication module 822 may provide a signal corresponding to the output of any state of the vehicle, the vehicle's surroundings, or any other information source connected to the vehicle via the bus. The vehicle data output may include, for example, an analog signal (such as the current speed), a digital signal provided by a separate information source (such as a clock, a thermometer, a position sensor such as a global positioning system (GPS) sensor, etc.), a digital signal propagated through a vehicle data network (such as an engine controller area network (CAN) bus through which engine-related information may be transmitted, a climate control CAN bus through which climate control-related information may be transmitted, and a multimedia data network through which multimedia data may be transmitted between multimedia components in the vehicle). For example, the onboard computing system 709 may retrieve the current speed of the vehicle estimated by the wheel sensor, the power state of the vehicle obtained via the vehicle's battery and / or power distribution system, the ignition state of the vehicle, etc. from the engine CAN bus. Additionally, other interfacing means such as Ethernet may also be used without departing from the scope of the present disclosure.

[0088] The storage device 808 may be included in the vehicle computing system 709 to store data in a non-volatile form, such as instructions that can be executed by the operating system processor 814 and / or the interface processor 820. The storage device 808 may store application data, including pre-recorded sounds, to enable the vehicle computing system 709 to run applications to connect to a cloud-based server and / or collect information for transmission to a cloud-based server. The application may retrieve information collected by vehicle systems / sensors, input devices (e.g., user interface 818), data stored in one or more storage devices (such as volatile memory 819A or non-volatile memory 819B), devices that communicate with the vehicle computing system (e.g., a mobile device connected via a Bluetooth® link), etc. The vehicle computing system 709 may also include volatile memory 819A. The volatile memory 819A may be random access memory (RAM). Non-transitory storage devices (such as non-volatile storage devices 808 and / or non-volatile memory 819B) may store instructions and / or codes that, when executed by a processor (e.g., operating system processor 814 and / or interface processor 820), control the onboard computing system 709 to perform one or more of the actions described in the present disclosure.

[0089] Microphone 802 may be included in the onboard computing system 709 to receive spoken commands from a user, measure ambient noise in the vehicle, determine whether audio from vehicle speakers is tuned to the acoustic environment of the vehicle, etc. A voice processing unit 804 may process spoken commands, such as those received from microphone 802. In some embodiments, the onboard computing system 709 may also be capable of using a microphone included in the vehicle's audio system 832 to receive spoken commands and sample ambient vehicle noise.

[0090] One or more additional sensors may be included in the sensor subsystem 810 of the vehicle computing system 709. For example, the sensor subsystem 810 may include a camera, such as a rear-view camera for assisting a user in parking the vehicle and / or a cabin camera for identifying a user (e.g., using facial recognition and / or user gestures). The sensor subsystem 810 of the vehicle computing system 709 may communicate with and receive input from various vehicle sensors and may further receive user input. For example, the input received by the sensor subsystem 810 may include a transmission gear position, a transmission clutch position, an accelerator pedal input, a brake input, a transmission selector position, a vehicle speed, an engine speed, a mass air flow through the engine, an ambient temperature, an intake air temperature, etc., as well as inputs from climate control system sensors (such as heat transfer fluid temperature, antifreeze temperature, fan speed, passenger compartment temperature, desired passenger compartment temperature, ambient humidity, etc.), an audio sensor for detecting a speech command issued by a user, a CID sensor for receiving commands from a CID of a remote keyless system of the vehicle and optionally tracking the geographic location / proximity of the CID, etc.

[0091] While certain vehicle system sensors may communicate solely with the sensor subsystem 810, other sensors may communicate with both the sensor subsystem 810 and the vehicle control system 830, or may communicate indirectly with the sensor subsystem 810 via the vehicle control system 830. The navigation subsystem 811 of the onboard computing system 709 may generate and / or receive navigation information, such as location information (e.g., via a GPS sensor and / or other sensors from the sensor subsystem 810), route guidance, traffic information, point of interest (POI) identification, and / or provide other navigation services for the driver.

[0092] The external device interface 812 of the onboard computing system 709 may be coupleable and / or in communication with one or more external devices 750 located outside the vehicle 702. Although the external devices are shown as being located outside the vehicle 702, it is understood that they may be temporarily housed in the vehicle 702, such as when a user operates the external device while operating the vehicle 702. In other words, the external device 750 is not integral to the vehicle 702. The external device 750 may include a mobile device 728 (e.g., connected via Bluetooth®, NFC, WI-FI Direct®, or other wireless connection) or an alternative Bluetooth®-enabled device 852.

[0093] The mobile device 728 may be a mobile phone, a smart phone, a wearable device / sensor, or other portable electronic device that can communicate with the vehicle-mounted computing system via wired and / or wireless communications. Other external devices include one or more external services 846. For example, the external device may include an off-vehicle device that is separate from the vehicle and located outside it. Other other external devices include one or more external storage devices 854, such as a solid-state drive, a pen drive, a universal serial bus (USB) drive, etc. Without departing from the scope of the present disclosure, the external device 750 may communicate with the vehicle-mounted computing system 709 wirelessly or via a connector. For example, the external device 750 may communicate with the vehicle-mounted computing system 709 through the network 860, a USB connection, a direct wired connection, a direct wireless connection, and / or other communication links through the external device interface 812.

[0094] The external device interface 812 may provide a communication interface to enable the vehicle computing system to communicate with a mobile device associated with the driver's contacts. For example, the external device interface 812 may enable a phone call to be established with the mobile device associated with the driver's contacts and / or a text message (e.g., short message service (SMS), multimedia message service (MMS), etc.) to be sent to the mobile device (e.g., via a cellular communication network). The external device interface 812 may additionally or alternatively provide a wireless communication interface to enable the vehicle computing system to synchronize data with one or more devices in the vehicle (e.g., the driver's mobile device) via Wi-Fi Direct®, as described in more detail below.

[0095] One or more applications 844 may be operable on the mobile device 728. As an example, the mobile device application 844 may be operable to aggregate user data regarding the user's interaction with the mobile device. For example, the mobile device application 844 may aggregate data regarding the following: a music playlist that the user listens to on the mobile device, a phone call log (including the frequency and duration of phone calls answered by the user), location information (including locations frequented by the user and the amount of time spent at each location), etc. The collected data may be transmitted by the application 844 to the external device interface 812 via the network 860. In addition, a specific user data request may be received from the onboard computing system 709 at the mobile device 728 via the external device interface 812. The specific data request may include a request to determine where the user's geographic location is, the ambient noise level and / or music genre at the user's location, the ambient weather conditions (temperature, humidity, etc.) at the user's location, etc. The mobile device application 844 can send control instructions to components (e.g., microphones, amplifiers, etc.) or other applications (e.g., navigation applications) of the mobile device 728 to enable the collection of requested data or the requested adjustments to the components on the mobile device. The mobile device application 844 can then relay the collected information back to the onboard computing system 709.

[0096] Likewise, one or more applications 848 may be operable on external services 846. As an example, external service applications 848 may be operable to aggregate and / or analyze data from multiple data sources. For example, external service applications 848 may aggregate data from one or more social media accounts of a user, data from an onboard computing system (e.g., sensor data, log files, user input, etc.), data from Internet queries (e.g., weather data, POI data), etc. The collected data may be sent to another device and / or analyzed by the application to determine the context of the driver, vehicle, and environment and perform actions based on the context (e.g., requesting / sending data to other devices).

[0097] The vehicle control system 830 may include controls for controlling aspects of various vehicle systems 831 involved in different in-vehicle functions. These may include, for example, controlling aspects of the vehicle audio system 832 for providing audio entertainment to vehicle occupants, aspects of the climate control system 834 for meeting the vehicle occupants' cabin cooling or heating needs, and aspects of the telecommunications system 836 for enabling vehicle occupants to establish telecommunications connections with others.

[0098] The audio system 832 may include one or more acoustic reproduction devices including electromagnetic transducers, such as one or more speakers 835. The vehicle audio system 832 may be passive, or active, such as by including a power amplifier. In some examples, the onboard computing system 709 may be the only audio source for the sound reproduction device, or there may be other audio sources (e.g., external devices such as mobile phones) connected to the audio reproduction system. The connection of any such external device to the audio reproduction device may be analog, digital, or any combination of analog and digital technologies.

[0099] The climate control system 834 may be configured to provide a comfortable environment within the cabin or passenger compartment of the vehicle 702. The climate control system 834 includes components that implement controlled ventilation, such as vents, heaters, air conditioners, integrated heater and air conditioner systems, etc. Other components connected to the heating and air conditioning equipment may include a windshield defrost and defogging system that can clean the windshield and a ventilation air filter for cleaning the outside air that enters the passenger compartment through the fresh air inlet.

[0100] The vehicle control system 830 may also include controls for adjusting settings of various vehicle control elements 861 (or vehicle controls, or vehicle system control elements) associated with the engine and / or auxiliary elements within the vehicle cabin, such as one or more steering wheel controls 862 (e.g., steering wheel mounted audio system controls, cruise controls, windshield wiper controls, headlight controls, turn signal controls, etc.), instrument panel controls, microphones, accelerator / brake / clutch pedals, shift levers, door / window controls located in the driver's door or passenger door, seat controls, cabin light controls, audio system controls, cabin temperature controls, etc. The vehicle control elements 861 may also include internal engine and vehicle operating controls (e.g., engine controller modules, actuators, valves, etc.) configured to receive instructions via the vehicle's CAN bus to change the operation of one or more of the engine, exhaust system, transmission, and / or other vehicle systems. The control signals may also control the audio output at one or more speakers 835 of the vehicle audio system 832. For example, the control signal may adjust audio output characteristics such as volume, balance, audio image (e.g., an audio signal configuration that produces audio output that appears to the user to be originating from one or more defined locations), audio distribution between multiple speakers, etc. Similarly, the control signal may control the vents, air conditioner, and / or heater of the climate control system 834. For example, the control signal may increase the delivery of cooling air to a particular section of the cab.

[0101] Control elements located outside the vehicle (e.g., controls for safety systems) may also be connected to the onboard computing system 709, such as via the inter-vehicle system communication module 822. The control elements of the vehicle control system 830 may be physically and permanently located on and / or in the vehicle for receiving user input. In addition to receiving control instructions from the onboard computing system 709, the vehicle control system 830 may also receive input from one or more external devices 750 operated by a user (such as from a mobile device 728). This allows various aspects of the vehicle system 831 and the vehicle control elements 861 to be controlled based on the user input received from the external device 750.

[0102] The onboard computing system 709 may also include one or more antennas 806. The onboard computing system may obtain broadband wireless Internet access via the antennas 806, and may also receive broadcast signals such as radio, television, weather, traffic, etc. The onboard computing system 709 may receive positioning signals such as GPS signals via the antennas 806. The onboard computing system may also receive wireless commands via RF (such as via the antennas 806) or via IR or other means through appropriate receiving devices. In some embodiments, the antennas 806 may be included as part of the audio system 832 or the telecommunications system 836. Additionally, the antennas 806 may provide AM / FM radio signals to the external device 750 (such as to the mobile device 728) via the external device interface 812.

[0103] One or more elements of the vehicle computing system 709 may be controlled by a user via a user interface 818. The user interface 818 may include a user interface such as Figure 7 The user may also interact with one or more applications of the onboard computing system 709 and the mobile device 728 via the user interface 818. In addition to receiving the user's vehicle setting preferences on the user interface 818, the vehicle settings selected by the onboard control system 830 may also be displayed to the user on the user interface 818. Notifications and other messages (e.g., received messages) and navigation assistance may be displayed to the user on the display of the user interface 818. User preferences / information and / or responses to presented messages may be executed via user input to the user interface 818.

[0104] As discussed herein, a behavioral security layer can be used to increase the security of a vehicle's remote keyless system and, therefore, the vehicle's internal components. The behavioral parameters of a user attempting to access the vehicle via the remote keyless system can be analyzed by an AI model trained to detect anomalies in user behavior. After the AI ​​model determines that the user's behavior is not associated with the behavior of a legitimate user and / or the AI ​​model identifies anomalies in the user's activity data (e.g., including behavioral parameters), an action can be performed. For example, the action can include generating an alert regarding an attempt to access the vehicle, avoiding allowing access to a password security layer, and / or allowing access to a password security layer.

[0105] The present disclosure also provides support for a method comprising: processing a transmission for operation of a remote keyless system for a vehicle, the remote keyless system having a behavioral security layer; determining whether the transmission is associated with a behavior of a legitimate user of the vehicle by using the behavioral security layer; and performing an action based on the determination that the transmission is not associated with the behavior of the legitimate user of the vehicle. In a first example of the method, the action includes at least one of: generating an alert about the transmission, and refraining from performing the operation. In a second example of the method that optionally includes the first example, the behavioral security layer includes an artificial intelligence model that has been trained using one or more behavioral parameters associated with a behavior corresponding to the transmission for operation of the remote keyless system. In a third example of the method optionally including one or both of the first and second examples, the behavior parameters include at least a predetermined number of parameters selected from a parameter set including: the time of day of the transmission, the date of the transmission, the location of the vehicle, the distance between the vehicle and the CID that sent the transmission, the number of operations of the CID per day, the time taken to open a door of the vehicle, the time taken to close the door, the force to open the door, the force to close the door, the temperature inside the vehicle, the temperature outside the vehicle, and humidity. In a fourth example of the method optionally including one or more or each of the first to third examples, the behavior parameters include all parameters of the parameter set. In a fifth example of the method optionally including one or more or each of the first to fourth examples, the behavior security layer is one of multiple security layers of the remote keyless system. In a sixth example of the method optionally including one or more or each of the first to fifth examples, the multiple security layers include one or more cryptographic security layers. In the seventh example of the method, which optionally includes one or more or each of the first to sixth examples, the one or more cryptographic security layers are used to determine whether the transmission is legal after determining whether the transmission is associated with abnormal behavior. In the eighth example of the method, which optionally includes one or more or each of the first to seventh examples, the remote keyless system includes at least one of the following: a remote keyless entry system and a remote keyless ignition system. In the ninth example of the method, which optionally includes one or more or each of the first to eighth examples, the operation is selected from a group including the following items: a door lock operation, a door unlock operation, an engine start operation, an engine stop operation, an anti-theft alarm activation operation, an anti-theft alarm deactivation operation, and an emergency signal operation. In the tenth example of the method, which optionally includes one or more or each of the first to ninth examples, the transmission is received by one of the following: an RF-based link, or an IR-based link.

[0106] The present disclosure also provides support for a method of ensuring access security to a vehicle, the method comprising: receiving a transmission to access a function of a remote keyless system of the vehicle, the remote keyless system having multiple security layers including a behavioral security layer; using a behavioral analysis model to analyze the behavior corresponding to the transmission; and performing an action based on the step of analyzing the behavior to detect anomalies in the behavior, wherein the behavioral analysis model has been trained using one or more parameters associated with the behavior corresponding to the transmission of the function of accessing the remote keyless system. In a first example of the method, the action includes at least one of the following: generating an alert about the transmission, and avoiding execution of the function. In a second example of the method that optionally includes the first example, the parameter associated with the behavior includes at least a predetermined number of parameters selected from a parameter set including the following items: the time of the day of the transmission, the date of the transmission, the location of the vehicle, the distance between the vehicle and the CID that sent the transmission, the number of operations of the CID per day, the time it takes to open the door of the vehicle, the time it takes to close the door, the force to open the door, the force to close the door, the temperature inside the vehicle, the temperature outside the vehicle, and the humidity. In a third example of the method, which optionally includes one or both of the first and second examples, the multiple security layers include one or more cryptographic security layers, and wherein the one or more cryptographic security layers are used to determine whether the transmission is legitimate after determining whether the transmission is associated with abnormal behavior.

[0107] The present disclosure also provides support for a remote keyless system for a vehicle, the remote keyless system comprising: one or more processors; and a non-volatile memory having executable instructions, the executable instructions, when executed, causing the one or more processors to: receive a transmission for an operation of the remote keyless system; analyze the behavior using a behavior analysis model and based on a parameter set of the behavior associated with the transmission; determine whether the behavior is not associated with a legitimate user of the vehicle based on the analysis of the behavior; and perform an action based on the determination that the behavior is not associated with a legitimate user of the vehicle, the action comprising at least one of the following: generating an alert about the operation and refraining from performing the operation, wherein the behavior analysis model has been trained using at least a predetermined number of the following behavior parameters: the time of day of the transmission, the date of the transmission, the location of the vehicle, the distance between the vehicle and the CID that sent the transmission, the number of operations of the CID per day, the time taken to open a door of the vehicle, the time taken to close the door, the force used to open the door, the force used to close the door, the temperature inside the vehicle, the temperature outside the vehicle, and the humidity. In a first example of the system, the one or more processors include at least one ECU of the vehicle, and wherein the non-transitory memory includes one or more non-volatile storage devices. In a second example of the system that optionally includes the first example, the multiple security layers include one or more cryptographic security layers, and wherein the one or more cryptographic security layers are used to determine whether the transmission is legal after determining whether the transmission is associated with abnormal behavior. In a third example of the system that optionally includes one or both of the first and second examples, the remote keyless system is integrated into an onboard computing system. In a fourth example of the system that optionally includes one or both or each of the first to third examples, the onboard computing system includes various parts of a vehicle receiver for receiving transmissions from at least one external device.

[0108] The description of the embodiments has been presented for the purpose of illustration and description. Suitable modifications and changes to the embodiments may be obtained by practicing the described methods in view of the above description. For example, unless otherwise specified, one or more of the described methods may be performed by suitable devices and / or device combinations. The described methods may be performed by executing stored instructions in combination with one or more logic devices (e.g., processors) in combination with one or more additional hardware elements (such as storage devices, memories, hardware network interfaces and / or antennas, switches, actuators, clock circuits, etc.). In addition to being performed in the order described in the application, in parallel and / or simultaneously, the described methods and associated actions may also be performed in various orders. The described systems are exemplary in nature and may include additional elements and / or omitted elements. The subject matter of the present disclosure includes all novel and non-obvious combinations and sub-combinations of the disclosed various systems and configurations and other features, functions and / or properties.

[0109] As used in this application, an element or step described in the singular and followed by the word "a" or "an" should be understood as not excluding a plurality of said elements or steps, unless such exclusion is stated. In addition, reference to "an embodiment" or "an example" of the present disclosure is not intended to be interpreted as excluding the existence of another embodiment that also incorporates the described features. Terms such as "first", "second", "third" are used only as markers, and are not intended to impose numerical requirements or specific positional order on their objects. As used herein, terms in which "and / or" language is used to present elements in a list represent any combination of the listed elements. For example, "A, B, and / or C" may mean any of the following: A alone; B alone; C alone; A and B; A and C; B and C; or A, B and C. The attached claims specifically point out the subject matter that is considered novel and non-obvious from the above disclosure.

Claims

1. A method, the method include: Processing transmissions for operation of a remote keyless system for a vehicle, the remote keyless system having a behavioral security layer; determining whether the transmission is associated with behavior of a legitimate user of the vehicle by using the behavioral security layer; as well as An action is performed based on a determination that the transmission is not associated with the behavior of the legitimate user of the vehicle.

2. The method of claim 1, wherein the action comprises at least one of: generating an alert regarding the transmission; and refraining from performing the operation.

3. The method of claim 1, wherein the behavioral security layer includes an artificial intelligence model that has been trained using one or more behavioral parameters associated with behaviors corresponding to transmissions for operation of the remote keyless system.

4. The method of claim 3, wherein the behavioral parameters include at least a predetermined number of parameters selected from a set of parameters including: time of day of the transmission; date of the transmission; location of the vehicle; distance between the vehicle and a customer identification device (CID) sending the transmission; number of operations per day of the CID; ; The time taken to open a door of the vehicle; The time taken to close the door; force to open the door; force to close the door; temperature inside the vehicle; temperature outside the vehicle; and humidity. The method of claim 4 , wherein the behavior parameters include all parameters of the parameter set. The method of claim 1 , wherein the behavioral security layer is one of a plurality of security layers of the remote keyless system.

7. The method of claim 6, wherein the plurality of security layers comprises one or more cryptographic security layers.

8. The method of claim 7, wherein the one or more cryptographic security layers are used to determine whether the transmission is legitimate after determining whether the transmission is associated with abnormal behavior.

9. The method of claim 1, wherein the remote keyless system comprises at least one of: a remote keyless entry system; and a remote keyless ignition system.

10. The method of claim 1, wherein the operation is selected from the group consisting of: a door lock operation; a door unlock operation; an engine start operation; an engine stop operation ; Activate anti-theft alarm operation; Deactivates the anti-theft alarm operation; and the emergency signal operation.

11. The method of claim 1 , wherein the transmission is received via one of: a radio frequency (RF) based link; or an infrared (IR) based link.

12. A method for ensuring secure access to a vehicle, the method include: receiving a transmission accessing functionality of a remote keyless system of the vehicle, the remote keyless system having a plurality of security layers, the plurality of security layers including a behavioral security layer; analyzing, using a behavioral analysis model, behavior corresponding to the transmission; as well as performing an action based on the step of analyzing the behavior to detect anomalies in the behavior, Wherein the behavior analysis model has been trained using one or more parameters associated with behavior corresponding to a transmission accessing a function of the remote keyless system.

13. The method of securing access to the vehicle of claim 12, wherein the action comprises at least one of: generating an alert regarding the transmission; and refraining from performing the function.

14. A method of securing access to a vehicle as claimed in claim 12, wherein the parameters associated with an action include at least a predetermined number of parameters selected from a set of parameters comprising: time of day of the transmission; date of the transmission; location of the vehicle; distance between the vehicle and a customer identification device (CID) sending the transmission; number of operations per day of the CID; ; The time taken to open a door of the vehicle; The time taken to close the door; force to open the door; force to close the door; temperature inside the vehicle; temperature outside the vehicle; and humidity.

15. The method of securing access to the vehicle as claimed in claim 12, wherein the plurality of security layers comprises one or more cryptographic security layers; and The one or more cryptographic security layers are used to determine whether the transmission is legitimate after determining whether the transmission is associated with abnormal behavior.

16. A remote keyless system for a vehicle, the remote keyless system include: one or more processors; as well as a non-transitory memory having executable instructions that, when executed, cause the one or more processors to: receiving a transmission for operation of the remote keyless system; analyzing the behavior using a behavior analysis model and based on a set of parameters of the behavior associated with the transmission; determining, based on the analysis of the behavior, whether the behavior is not associated with a legitimate user of the vehicle; as well as performing an action based on a determination that the behavior is not associated with the legitimate user of the vehicle, the action comprising at least one of: generating an alert regarding the operation; and refraining from performing said operations, wherein the behavior analysis model has been trained using at least a predetermined number of the following behavior parameters: time of day of the transmission; date of the transmission; location of the vehicle; distance between the vehicle and a customer identification device (CID) sending the transmission; number of operations of the CID per day; The time taken to open a door of the vehicle; The time taken to close the door; the force to open the door; the force to close the door; the temperature inside the vehicle; the temperature outside the vehicle; and humidity.

17. The remote keyless system of claim 16, wherein the one or more processors include at least one electronic control unit (ECU) of the vehicle; and The non-transitory memory includes one or more non-volatile memory devices.

18. The remote keyless system as claimed in claim 16, wherein the plurality of security layers includes one or more cryptographic security layers; and The one or more cryptographic security layers are used to determine whether the transmission is legitimate after determining whether the transmission is associated with abnormal behavior.

19. The remote keyless system of claim 16, wherein the remote keyless system is integrated into an onboard vehicle computing system.

20. The remote keyless system of claim 19, wherein the onboard computing system includes portions of a vehicle receiver for receiving transmissions from at least one external device.