Vehicle network federated forgetting learning method and system based on group learning and homomorphic encryption

Abstract

The present invention belongs to the field of privacy protection technology and discloses a vehicle network federated forgetting learning method and system based on group learning and homomorphic encryption, including building a model and training; a target vehicle node issues a forgetting request, an RSU node sends global model parameters to the target vehicle node for reverse correction training, uploads the reverse corrected model parameters to the RSU node to calculate the rate of change of the model parameters, non-target vehicle nodes perform forward correction training on the reverse corrected model parameters, sends the forward corrected parameters to the RSU node for edge aggregation, and obtains an SL forgetting model; when the rate of change of the model parameters is less than a set threshold, the target vehicle node exits the federated system, the correction training ends, and the RSU node uploads the SL forgetting model parameters to the server to update the global model. The present invention can effectively eliminate toxic data samples, achieve a balance between model performance and retraining overhead, and protect the privacy of vehicle nodes without compromising model performance.

Description

Technical Field

[0001] The present invention relates to the field of privacy protection technology, and in particular to a method and system for federated forgetting learning in an Internet of Vehicles (IoV) based on group learning and homomorphic encryption. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the acceleration of urbanization, traditional traffic management methods are no longer able to effectively cope with increasingly complex traffic conditions, and the demand for intelligent transportation is rapidly increasing. Against this backdrop, the concept of Intelligent Transportation Systems (ITS) has emerged, offering new solutions to improve traffic efficiency and safety. Within this system, the Internet of Vehicles (IoV) plays a crucial role. Vehicles in an IoV continuously collect data on their own status (such as speed, location, and fuel consumption) and surrounding environment (such as road conditions, pedestrians, and other vehicles) through built-in sensors (such as cameras, radar, GPS, and LIDAR). These vehicles exchange and share data in real time with other vehicles, road infrastructure, and cloud systems through onboard communication systems, providing strong support for creating a safer and more efficient traffic environment. While IoV offers significant advantages, it also comes with numerous challenges. The high mobility and ever-changing topology of IoV environments pose significant security and privacy risks to users sharing information. Therefore, ensuring secure data sharing without compromising user privacy is crucial in IoVs.

[0004] Machine learning (ML) is considered a promising technology for improving driving safety and enabling intelligent traffic management. However, due to factors such as latency requirements, bandwidth limitations, computing resources, and privacy protection, traditional centralized ML approaches are unable to process the massive amounts of data generated by the Internet of Things (IoV). To address this, researchers have proposed using federated learning (FL) to overcome the limitations of centralized ML. As an effective means of protecting data privacy, FL not only enables AI collaboration without exposing local data privacy, technically breaking down data silos, but also avoids centralized data storage and transmission, effectively reducing bandwidth and computing pressures, making it more adaptable to the complex data environment of the Internet of Things (IoV). However, the FL mechanism still presents security issues such as privacy leakage. First, model parameters or gradients are essentially relational mappings of the original dataset. Even if the data is not directly shared, attackers can still restore part or all of the original data based on the model parameters or gradients. Second, attackers can infer information about the original training data through model inversion attacks. In IoV scenarios, data may contain a wealth of sensitive information, including driving routes, location records, and driving habits. This data not only records user activity trajectories but also involves personal privacy. When an individual's identity changes or users need to protect their privacy, the leakage of this information raises serious privacy concerns. Furthermore, the EU General Data Protection Regulation (GDPR) stipulates that citizens have a "right to be forgotten" regarding their own data. Therefore, effective techniques are needed to delete or forget specific training data from a trained FL model.

[0005] To address these issues, federated forgetting (FU) offers unique advantages. It aims to selectively remove specific training data points and their impact on the trained model, rendering the updated model as if it had never been trained on these data points. FU provides a "subtractive" capability that effectively removes unauthorized, malicious, or outdated data points without the resource-intensive task of full retraining. FU is a migration from existing forgetting techniques in the ML context. Its application enables models to more efficiently meet dynamic privacy requirements and regulatory compliance. However, as FU technology evolves, optimizing computational resources and communication overhead while ensuring model performance and strengthening privacy protection during the forgetting process remain important research directions. Current research primarily focuses on protecting the privacy of raw data, while rarely addressing the privacy of both forgotten and non-forgotten parameters. This allows attackers to potentially recover private information through these parameters, potentially leaking client privacy. Furthermore, federated forgetting incurs additional computational and communication overhead, and existing solutions often rely on space savings for time, making it difficult to deploy forgetting at scale. Summary of the Invention

[0006] In order to solve the above problems, the present invention proposes a federated forgetting learning method and system for the Internet of Vehicles based on group learning and homomorphic encryption. By introducing homomorphic encryption technology, the forgetting operation is effectively performed without decryption, protecting the privacy of the forgotten and non-forgotten parameters of vehicle nodes; combined with group learning technology to perform intra-group forgetting, a balance is achieved between model performance and retraining overhead.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a method for forgetting learning in a federated Internet of Vehicles (IoV) based on group learning and homomorphic encryption, comprising the following steps:

[0009] Build a federated learning model for the Internet of Vehicles and train the model;

[0010] When the target vehicle node issues a forget request, the RSU node to which it belongs downloads the encrypted global model parameters from the aggregation server and sends them to the target vehicle node. The target vehicle node decrypts the global model parameters and performs multiple rounds of reverse correction training on them. The reverse-corrected model parameters are encrypted and uploaded to the RSU node. The RSU node calculates the rate of change of the model parameters and sends the reverse-corrected model parameters to the non-target vehicle nodes in the same group as the target vehicle node. The non-target vehicle nodes perform forward correction training on the reverse-corrected model parameters. In each round of forward correction training, the non-target vehicle nodes in the group perform homomorphic encryption on the correction parameter updates and exchange encrypted correction updates with adjacent non-target vehicle nodes. Other non-target vehicle nodes aggregate the received encrypted correction updates with their own correction updates for the next round of forward correction training. Finally, all non-target vehicle nodes encrypt the correction updates and send them to the RSU nodes to which the group belongs for edge aggregation to obtain the SL forgetting model.

[0011] When the rate of change of the model parameters calculated by the RSU node is less than the set threshold, the target vehicle node exits the federation system, the correction training ends, and the RSU node uploads the SL forgetting model parameters to the server. The server updates the global model by aggregating the SL forgetting model parameters.

[0012] As an optional implementation, the Internet of Vehicles federated learning model includes a server, an RSU node, and a vehicle node, wherein a plurality of RSU nodes are provided at the lower layer of the server, and a plurality of vehicle nodes divided into different groups are provided within the area of ​​each RSU node.

[0013] As an optional implementation method, the IoV federated learning model is trained as follows:

[0014] The RSU node downloads the encrypted global model parameters of the current round from the server and then sends them to the vehicle nodes of each group in its area. The vehicle node decrypts the global model parameters and adjusts them based on local data to generate local updates. The local updates are then encrypted and uploaded to the RSU node to which the group belongs. The RSU node performs edge aggregation on the encrypted local updates uploaded by each vehicle node to generate an SL model and submits the SL model parameters and aggregation weights to the server. The server updates the global model through the aggregation weights of each RSU node and sends the updated global model to each RSU node for the next round of training until the global model converges and a trained Internet of Vehicles federated learning model is obtained.

[0015] As an optional implementation, it also includes passively forgetting the vehicle node, and the passive forgetting is:

[0016] During the training of the federated learning model of the Internet of Vehicles, before the RSU node performs edge aggregation on the encrypted local updates uploaded by each vehicle node, it will calculate the cosine similarity between the encrypted local updates submitted by each vehicle node and the SL model parameters. When the result deviates significantly, it is regarded as a malicious node. The contribution of the malicious node is removed based on the historical global model, and k rounds of retraining are performed. The new local update is encrypted and submitted to the RSU node to bridge the remaining node weights for edge aggregation.

[0017] As an optional implementation method, a federated learning model for the Internet of Vehicles is constructed, specifically as follows:

[0018] Register RSU nodes and vehicle nodes, assign initial reputation values ​​to each node, and store successfully registered node information on the blockchain;

[0019] Initialize a machine learning model and broadcast it to all registered vehicle nodes that meet the task requirements through the RSU node to respond to the task;

[0020] RSU nodes and vehicle nodes that wish to participate in the federated learning task send a response message to the blockchain, and nodes with higher reputation values ​​are selected to participate in the task;

[0021] The RSU node divides the vehicle nodes that have successfully joined the training task in its area into multiple different groups based on data distribution, and all vehicle nodes in the group are connected to the blockchain.

[0022] As an optional implementation, the vehicle node decrypts the global model parameters, specifically:

[0023] The nodes participating in the federated learning task collaboratively execute the key generation protocol to generate public keys and private key shares. The vehicle nodes interact point-to-point through the blockchain, exchange private key shares, and reconstruct the private key using Lagrange interpolation, which is then used to decrypt the global model parameters.

[0024] In a second aspect, the present invention provides a federated forgetting learning system for Internet of Vehicles based on group learning and homomorphic encryption, comprising:

[0025] The model building and training module is configured to: build a federated learning model for the Internet of Vehicles and train the model;

[0026] The model correction training module is configured as follows: when the target vehicle node issues a forget request, the RSU node to which it belongs downloads the encrypted global model parameters from the aggregation server and sends them to the target vehicle node. The target vehicle node decrypts the global model parameters and performs multiple rounds of reverse correction training on them. The reverse-corrected model parameters are encrypted and uploaded to the RSU node. The RSU node calculates the rate of change of the model parameters and sends the reverse-corrected model parameters to the non-target vehicle nodes in the same group as the target vehicle node. The non-target vehicle nodes perform forward correction training on the reverse-corrected model parameters. In each round of forward correction training, the non-target vehicle nodes in the group perform homomorphic encryption on the correction parameter updates and exchange encrypted correction updates with adjacent non-target vehicle nodes. Other non-target vehicle nodes aggregate the received encrypted correction updates with their own correction updates for the next round of forward correction training. Finally, all non-target vehicle nodes encrypt the correction updates and send them to the RSU nodes to which the group belongs for edge aggregation to obtain the SL forgetting model.

[0027] The global model update module is configured as follows: when the rate of change of the model parameters calculated by the RSU node is less than the set threshold, the target vehicle node exits the federation system, the correction training ends, the RSU node uploads the SL forgetting model parameters to the server, and the server updates the global model by aggregating the SL forgetting model parameters.

[0028] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0029] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0030] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present disclosure proposes a federated forgetting learning method and system for the Internet of Vehicles based on group learning and homomorphic encryption. Compared with existing technologies, the present disclosure performs edge aggregation at the RSU node, effectively reducing communication and computing pressure; by introducing a group learning mechanism, multiple vehicle nodes can work together to further optimize the efficiency of forgetting learning and ensure the stability of model performance; a threshold homomorphic encryption algorithm is used to protect model parameters, prevent unauthorized access, effectively protect model updates, and prevent model inversion attacks and attacks from untrusted servers.

[0033] This paper proposes a federated forgetting learning method and system for the Internet of Vehicles based on group learning and homomorphic encryption. Compared with the existing technology that does not use blockchain, this paper uses blockchain point-to-point communication to reconstruct the decryption private key, while enabling group learning to accelerate the forgetting process; achieving decentralized and secure federated learning, and ultimately ensuring the secure on-chain storage of global models, historical updates and reputation values, providing a transparent and tamper-proof chain of evidence, and laying the foundation for the sustainable development of the Internet of Vehicles.

[0034] The present disclosure proposes a method and system for federated forgetting learning in the Internet of Vehicles based on group learning and homomorphic encryption. Compared with the existing technology that does not use the homomorphic encryption algorithm, the present disclosure utilizes the characteristics of the homomorphic encryption algorithm to achieve secure aggregation of encrypted local updates during the transmission of local updates, effectively preventing model inversion attacks; and utilizes the secret sharing algorithm to achieve private key splitting, ensuring data privacy and model security, and effectively guaranteeing the robustness and stability of the federated learning process.

[0035] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0037] Figure 1 A framework for a federated forgetting learning method for Internet of Vehicles based on group learning and homomorphic encryption provided in Example 1 of the present invention Figure 1 ;

[0038] Figure 2 A framework for a federated forgetting learning method for Internet of Vehicles based on group learning and homomorphic encryption provided in Example 1 of the present invention Figure 2 ;

[0039] Figure 3 A flowchart of a federated forgetting learning method for Internet of Vehicles based on group learning and homomorphic encryption provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0043] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0044] Explanation of terms:

[0045] 1. Blockchain: Blockchain is a distributed ledger technology that uses a series of encryption algorithms and consensus mechanisms to connect data in chronological order in the form of blocks to form an unalterable record chain.

[0046] 2. Federated Learning: Federated Learning (FL) is a decentralized machine learning method that allows multiple parties to collaborate on training a shared model without exposing the original data.

[0047] 3. Internet of Vehicles: The Internet of Vehicles (IoV) is a comprehensive system that leverages information and communication technologies to facilitate connectivity between vehicles and between them and the external environment. Its core concept is to enable real-time connectivity between vehicles and the outside world through information and communication technologies (ICT), thereby improving traffic efficiency, reducing accidents, optimizing energy consumption, and providing a more intelligent driving experience.

[0048] 4. Federated Unlearning: Machine Unlearning (MU) aims to effectively remove specific training samples and their influence from a trained model while minimizing model performance. With the real-world deployment of Federated Learning (FL), it allows multiple parties to jointly train a shared model without sharing the original data. However, because model parameters or gradient information are still relational mappings of the original dataset, security issues such as privacy leakage still exist. Therefore, it is necessary to extend MU to Federated Unlearning (FU) to protect client privacy.

[0049] 5. Homomorphic encryption: Homomorphic encryption (HE) is a specialized encryption technique that allows computations to be performed directly on ciphertext without decrypting the data, ensuring that the resulting result is consistent with the plaintext. The advantages of homomorphic encryption include low communication overhead, the elimination of multiple rounds of communication, a secure computational process, and the protection of the parties involved in the computation.

[0050] Example 1

[0051] like Figure 1-3 As shown, this embodiment provides a vehicle network federation forgetting learning method based on group learning and homomorphic encryption, including the following steps:

[0052] S1 builds a federated learning model for the Internet of Vehicles and trains the model;

[0053] S2 When the target vehicle node issues a forget request, the RSU node to which it belongs downloads the encrypted global model parameters from the aggregation server and sends them to the target vehicle node. The target vehicle node decrypts the global model parameters and performs multiple rounds of reverse correction training on them. The reverse-corrected model parameters are encrypted and uploaded to the RSU node. The RSU node calculates the rate of change of the model parameters and sends the reverse-corrected model parameters to the non-target vehicle nodes in the same group as the target vehicle node. The non-target vehicle nodes perform forward correction training on the reverse-corrected model parameters. In each round of forward correction training, the non-target vehicle nodes in the group perform homomorphic encryption on the correction parameter updates and exchange encrypted correction updates with adjacent non-target vehicle nodes. Other non-target vehicle nodes aggregate the received encrypted correction updates with their own correction updates for the next round of forward correction training. Finally, all non-target vehicle nodes encrypt the correction updates and send them to the RSU nodes to which the group belongs for edge aggregation to obtain the SL forgetting model.

[0054] S3 When the rate of change of the model parameters calculated by the RSU node is less than the set threshold, the target vehicle node exits the federation system, the correction training ends, and the RSU node uploads the SL forgetting model parameters to the server. The server updates the global model by aggregating the SL forgetting model parameters.

[0055] First, it is necessary to build a federated learning model for the Internet of Vehicles, which includes a server, RSU nodes and vehicle nodes. The lower layer of the server is equipped with multiple RSU nodes, and each RSU node has multiple vehicle nodes divided into different groups in its area.

[0056] The specific process of building a federated learning model for the Internet of Vehicles is as follows:

[0057] 1. Identity registration phase: The smart contract automatically executes the registration process for all RSU nodes and vehicle nodes, assigns an initial reputation value to each node, and stores the information of successfully registered nodes on the chain.

[0058] 2. Task Release Phase: The task publisher initializes a machine learning model and uploads it to the aggregation server. After the smart contract interacts with the task publisher to confirm the order, it broadcasts the task to all registered vehicle nodes that meet the task requirements through the RSU node.

[0059] 3. Participating Node Selection Phase: RSU nodes and vehicle nodes wishing to participate in the federated learning task send a response message to the aggregation server. The smart contract retrieves the recent reputation of the responding node from the blockchain, and the task publisher selects the node with the highest reputation to participate in the task.

[0060] 4. Group Division: Integrate Swarm Learning (SL) into Federated Forget Learning (FU) to build a two-layer federated forget learning architecture. Based on the federated learning task, the RSU node divides the vehicle nodes in its region that have successfully joined the training task into p different groups. Vehicle nodes within the group must connect to the blockchain to achieve secure peer-to-peer communication.

[0061] The constructed IoV federated learning model is trained as follows:

[0062] Model distribution stage:

[0063] The RSU node downloads the encrypted global model parameters of the current round from the server and then sends them to the vehicle nodes of each group in its area.

[0064] Privacy-preserving training phase:

[0065] To decrypt the global model, the nodes participating in the federated learning task collaboratively execute the key generation protocol to generate public keys and private key shares. Vehicle nodes interact point-to-point through the blockchain, exchange private key shares, and reconstruct the private key using Lagrange interpolation, which is then used to decrypt the global model parameters.

[0066] Based on the federated learning protocol, the vehicle nodes in the group perform local training and generate local updates based on the distributed global model (the global model can be public at the time of initialization, and the subsequent global model is encrypted. The vehicle nodes need to exchange private key shares through the blockchain point-to-point and reconstruct the aggregation structure through Lagrange interpolation, and finally use the private key to decrypt the global model).

[0067] Threshold homomorphic encryption: the vehicle node calls Encrypt(m, PK) to encrypt the local update and uploads the encrypted local update to the RSU node to which the group belongs, along with indicators such as the local data size, computing speed, and training time, as the basis for reputation evaluation.

[0068] Edge aggregation: The RSU node aggregates the encrypted local updates uploaded by each vehicle node. During the edge aggregation process, the RSU node is used as a participant in the edge aggregation process. After receiving the encrypted local updates uploaded by the SL group, the RSU node first verifies whether the identity and timestamp of the vehicle node are valid. After verification, the encrypted local updates are edge aggregated to generate the SL model. The RSU node retains the historical updates submitted by the SL group in each edge aggregation round. The RSU node submits the SL model parameters and aggregation weights aggregated by the edge to the aggregation server for global model aggregation.

[0069] Global aggregation: The aggregation server retains the historical model parameters submitted by each RSU node and updates the global model using the aggregated weights of each RSU node. Ultimately, a global model is generated through intra-group and inter-group aggregation, enabling hierarchical federated learning. The updated global model is then distributed to each RSU node for the next round of training. This process continues until the global model converges, resulting in a trained IoV federated learning model. Encrypted model parameters and the reputation of participating nodes are stored on the blockchain, ensuring the security and traceability of model updates.

[0070] Forgetting learning stage:

[0071] Forgetting learning includes active forgetting learning and passive forgetting learning. The specific process of active forgetting learning is as follows:

[0072] The target vehicle node sends a forget request, assuming that i During round training, the target vehicle node is received When a forget request is made, the ultimate goal is to exclude the data influence of this node from the global model.

[0073] During the reverse correction training phase, the blockchain first verifies the identity of the vehicle node that initiates the forget request. After verification, the RSU node sends the newly downloaded encrypted global model parameters to the target vehicle node. The target vehicle node conducts point-to-point interaction through the blockchain, exchanges private key shares, and reconstructs the private key using Lagrange interpolation. Finally, the private key is used to decrypt the global model.

[0074] The target vehicle node adjusts the local update size and update direction using a gradient ascent algorithm, gradually eliminating the impact of local data on the global model. After every n rounds of reverse correction training, the target vehicle node exchanges the corrected encrypted model parameters with the RSU node.

[0075] The RSU node calculates the rate of change of the model parameters, and the SL corrects the rate of change of the model parameters as follows:

[0076]

[0077] in, is the parameter of the SL correction model in round t, is the rate of change of the parameter, when Less than the set threshold When , the model is considered to have converged, and the reverse correction training is stopped. The SL model after reverse correction training is expressed as:

[0078]

[0079] in, represents the modified SL model, represents the corrected update of the target vehicle node, Represents the learning rate, which is a hyperparameter that controls the magnitude of each update. Represents the loss function L relative to the correction update gradient.

[0080] In the forward correction training phase, the RSU node sends the reverse correction model parameters to the non-target vehicle nodes in the same group as the target vehicle node. The non-target vehicle nodes use the reverse correction model to Perform n rounds of forward correction training. In each round of forward correction training, each non-target vehicle node Will calculate the correction update , after encryption, it interacts with adjacent non-target vehicle nodes. Other non-target vehicle nodes aggregate the received encrypted correction updates with their own correction updates for the next round of forward correction training. Finally, all non-target vehicle nodes encrypt the correction updates and send them to the RSU node to which the SL group belongs for edge aggregation to obtain the SL forgetting model.

[0081] Aggregate correction update, RSU node aggregates correction updates from non-target vehicle nodes To update the SL forgetting model, the corrected updated aggregation results are as follows:

[0082]

[0083] in, is the weight of the non-target vehicle node.

[0084] SL forgetting model update,By aggregating the edges of the correction update, the SL forgetting model can be updated as:

[0085]

[0086] Each time the target vehicle node interacts with the RSU node to correct the model parameters, it needs to perform forward correction training until the change rate of the SL correction model parameters is less than the set threshold. , the target vehicle node exits the federated system. After the correction training is completed, the RSU node uploads the SL forgetting model parameters to the server, and the server updates the global model by aggregating the SL forgetting model parameters.

[0087] The specific process of passive forgetting is as follows:

[0088] Before the RSU node performs edge aggregation on the encrypted local updates uploaded by each vehicle node, the cosine similarity between the encrypted local updates submitted by each vehicle node and the SL model is calculated. When the result deviates significantly, it is regarded as a malicious node. The contribution of the malicious node is removed based on the historical global model, and k rounds of retraining are performed. The new local update is encrypted and submitted to the RSU node, and the remaining node weights are bridged for edge aggregation to offset the impact of the malicious node on the global model.

[0089] Reconstruction phase:

[0090] The server updates the global model by aggregating the SL forgetting model parameters and updates the global FL model to:

[0091]

[0092] in, is the current global model Based on the revised global model.

[0093] The aggregation server, target vehicle node and non-target vehicle node repeat the above process together, and finally obtain the forgotten global model , the model has eliminated the target vehicle node The impact of data.

[0094] The present disclosure utilizes group learning technology, and the vehicle nodes in each group can share and jointly train the corresponding SL model, thereby improving the adaptability and accuracy of the model, realizing hierarchical federated learning through intra-group aggregation and inter-group aggregation, and reducing communication overhead. The homomorphic encryption algorithm is used to perform model aggregation based on the ciphertext domain of the model parameters of the vehicle nodes during the training process, providing a strong privacy guarantee for FL and avoiding inference attacks by malicious RSU nodes. Before aggregation, the model parameters are screened by calculating the cosine similarity between the local model parameters of each vehicle node and the SL model parameters to prevent model poisoning attacks. During each training process, the task publisher performs accurate and effective reputation evaluation on the RSU nodes and vehicle nodes based on relevant indicators, and stores the reputation value securely on the chain, ultimately achieving a safe and efficient federated forgetting process.

[0095] Example 2

[0096] This embodiment provides a federated forgetting learning system for Internet of Vehicles based on group learning and homomorphic encryption, including:

[0097] The model building and training module is configured to: build a federated learning model for the Internet of Vehicles and train the model;

[0098] The model correction training module is configured as follows: when the target vehicle node issues a forget request, the RSU node to which it belongs downloads the encrypted global model parameters from the aggregation server and sends them to the target vehicle node. The target vehicle node decrypts the global model parameters and performs multiple rounds of reverse correction training on them. The reverse-corrected model parameters are encrypted and uploaded to the RSU node. The RSU node calculates the rate of change of the model parameters and sends the reverse-corrected model parameters to the non-target vehicle nodes in the same group as the target vehicle node. The non-target vehicle nodes perform forward correction training on the reverse-corrected model parameters. In each round of forward correction training, the non-target vehicle nodes in the group perform homomorphic encryption on the correction parameter updates and exchange encrypted correction updates with adjacent non-target vehicle nodes. Other non-target vehicle nodes aggregate the received encrypted correction updates with their own correction updates for the next round of forward correction training. Finally, all non-target vehicle nodes encrypt the correction updates and send them to the RSU nodes to which the group belongs for edge aggregation to obtain the SL forgetting model.

[0099] The global model update module is configured as follows: when the rate of change of the model parameters calculated by the RSU node is less than the set threshold, the target vehicle node exits the federation system, the correction training ends, the RSU node uploads the SL forgetting model parameters to the server, and the server updates the global model by aggregating the SL forgetting model parameters.

[0100] It should be noted that the above modules correspond to the steps described in Example 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above Example 1. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0101] In further embodiments, there is also provided:

[0102] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed by the processor, wherein when the computer instructions are executed by the processor, the method described in Example 1 is performed. For the sake of brevity, no further details are given here.

[0103] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0104] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0105] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in Example 1 is performed.

[0106] The method in Example 1 can be directly implemented as a hardware processor, or can be implemented using a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, it will not be described in detail here.

[0107] A computer program product includes a computer program, which implements the method described in embodiment 1 when executed by a processor.

[0108] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions contained in program modules, which are executed in a device on a real or virtual processor of a target to perform the process / method described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided between program modules as needed. The machine-executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0109] The computer program code for implementing the method of the present invention can be written in one or more programming languages. These computer program codes can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the computer or other programmable data processing device, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on a computer, partially on a computer, as an independent software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0110] In the context of the present invention, computer program code or related data can be carried by any appropriate carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals include electrical, optical, radio, acoustic, or other forms of propagated signals, such as carrier waves, infrared signals, and the like.

[0111] Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A federated forgetting learning method for Internet of Vehicles based on group learning and homomorphic encryption, characterized by: The following steps are involved: Build a federated learning model for the Internet of Vehicles and train the model; When the target vehicle node issues a forget request, the RSU node to which it belongs downloads the encrypted global model parameters from the aggregation server and sends them to the target vehicle node. The target vehicle node decrypts the global model parameters and performs multiple rounds of reverse correction training on them. The reverse-corrected model parameters are encrypted and uploaded to the RSU node. The RSU node calculates the rate of change of the model parameters and sends the reverse-corrected model parameters to the non-target vehicle nodes in the same group as the target vehicle node. The non-target vehicle nodes perform forward correction training on the reverse-corrected model parameters. In each round of forward correction training, the non-target vehicle nodes in the group perform homomorphic encryption on the correction parameter updates and exchange encrypted correction updates with adjacent non-target vehicle nodes. Other non-target vehicle nodes aggregate the received encrypted correction updates with their own correction updates for the next round of forward correction training. Finally, all non-target vehicle nodes encrypt the correction updates and send them to the RSU nodes to which the group belongs for edge aggregation to obtain the SL forgetting model. When the rate of change of the model parameters calculated by the RSU node is less than the set threshold, the target vehicle node exits the federation system, the correction training ends, and the RSU node uploads the SL forgetting model parameters to the server. The server updates the global model by aggregating the SL forgetting model parameters.

2. The method for forgetting learning in a federated Internet of Vehicles based on group learning and homomorphic encryption according to claim 1, characterized in that: The Internet of Vehicles federated learning model includes a server, an RSU node and a vehicle node, wherein a plurality of RSU nodes are provided at the lower layer of the server, and a plurality of vehicle nodes divided into different groups are provided within the area of ​​each RSU node.

3. The method for forgetting learning in a federated Internet of Vehicles based on group learning and homomorphic encryption according to claim 1, wherein: Training the IoV federated learning model, specifically: The RSU node downloads the encrypted global model parameters of the current round from the server and then sends them to the vehicle nodes of each group in its area. The vehicle node decrypts the global model parameters and adjusts them based on local data to generate local updates. The local updates are then encrypted and uploaded to the RSU node to which the group belongs. The RSU node performs edge aggregation on the encrypted local updates uploaded by each vehicle node to generate an SL model and submits the SL model parameters and aggregation weights to the server. The server updates the global model through the aggregation weights of each RSU node and sends the updated global model to each RSU node for the next round of training until the global model converges and a trained Internet of Vehicles federated learning model is obtained.

4. The method for forgetting learning in a federated Internet of Vehicles based on group learning and homomorphic encryption as claimed in claim 3, characterized in that: It also includes passively forgetting the vehicle node, and the passive forgetting is: During the training of the federated learning model of the Internet of Vehicles, before the RSU node performs edge aggregation on the encrypted local updates uploaded by each vehicle node, it will calculate the cosine similarity between the encrypted local updates submitted by each vehicle node and the SL model parameters. When the result deviates significantly, it is regarded as a malicious node. The contribution of the malicious node is removed based on the historical global model, and k rounds of retraining are performed. The new local update is encrypted and submitted to the RSU node to bridge the remaining node weights for edge aggregation.

5. The method for forgetting learning in a federated Internet of Vehicles based on group learning and homomorphic encryption according to claim 1, wherein: Build a federated learning model for the Internet of Vehicles, specifically: Register RSU nodes and vehicle nodes, assign initial reputation values ​​to each node, and store successfully registered node information on the blockchain; Initialize a machine learning model and broadcast it to all registered vehicle nodes that meet the task requirements through the RSU node to respond to the task; RSU nodes and vehicle nodes that wish to participate in the federated learning task send a response message to the blockchain, and nodes with higher reputation values ​​are selected to participate in the task; The RSU node divides the vehicle nodes that have successfully joined the training task in its area into multiple different groups based on data distribution, and all vehicle nodes in the group are connected to the blockchain.

6. The method for forgetting learning in a federated Internet of Vehicles based on group learning and homomorphic encryption according to claim 1, wherein: The vehicle node decrypts the global model parameters, specifically: The nodes participating in the federated learning task collaboratively execute the key generation protocol to generate public keys and private key shares. The vehicle nodes interact point-to-point through the blockchain, exchange private key shares, and reconstruct the private key using Lagrange interpolation, which is then used to decrypt the global model parameters.

7. The Internet of Vehicles federated forgetting learning system based on group learning and homomorphic encryption is characterized by: include: The model building and training module is configured to: build a federated learning model for the Internet of Vehicles and train the model; The model correction training module is configured as follows: when the target vehicle node issues a forget request, the RSU node to which it belongs downloads the encrypted global model parameters from the aggregation server and sends them to the target vehicle node. The target vehicle node decrypts the global model parameters and performs multiple rounds of reverse correction training on them. The reverse-corrected model parameters are encrypted and uploaded to the RSU node. The RSU node calculates the rate of change of the model parameters and sends the reverse-corrected model parameters to the non-target vehicle nodes in the same group as the target vehicle node. The non-target vehicle nodes perform forward correction training on the reverse-corrected model parameters. In each round of forward correction training, the non-target vehicle nodes in the group perform homomorphic encryption on the correction parameter updates and exchange encrypted correction updates with adjacent non-target vehicle nodes. Other non-target vehicle nodes aggregate the received encrypted correction updates with their own correction updates for the next round of forward correction training. Finally, all non-target vehicle nodes encrypt the correction updates and send them to the RSU nodes to which the group belongs for edge aggregation to obtain the SL forgetting model. The global model update module is configured as follows: when the rate of change of the model parameters calculated by the RSU node is less than the set threshold, the target vehicle node exits the federation system, the correction training ends, the RSU node uploads the SL forgetting model parameters to the server, and the server updates the global model by aggregating the SL forgetting model parameters.

8. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 6 is completed.

9. A computer-readable storage medium, characterized in that Used to store computer instructions, which, when executed by a processor, complete the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which is used to implement the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images