With the rapid development of intelligent transportation systems, federated learning (FL) has made remarkable progress in vehicular ad-hoc networks (VANETs), establishing itself as a crucial approach to improve data sharing efficiency and privacy protection. However, the existing solutions face significant challenges arising from the dynamic nature of the networks, the rapid mobility of vehicles, and frequent environmental changes, particularly in terms of privacy preservation, malicious vehicle management, verification mechanisms, and so on. To address these challenges, a novel and verifiable FL scheme for VANETs is proposed in this paper. First, an enhanced Paillier homomorphic encryption algorithm is integrated into the framework, which not only strengthens privacy protection but also reduces computational overhead, thus meeting the frequent data processing requirements of VANETs. Second, a malicious vehicle revocation and tracking mechanism, based on group keys and the cosine similarity, is introduced to manage the dynamic joining and leaving of malicious vehicles, thereby enhancing the overall security of the system. Finally, a lightweight aggregate signature verification mechanism is implemented using elliptic curve-based certificate-free signatures, effectively mitigating the high overhead typically associated with traditional certificate management while reducing the storage and communication burdens on vehicles, thereby improving the efficiency of message authentication. Meanwhile, the communication environment and vehicle dynamic information processing mechanism are optimized to enhance the scheme’s adaptability to the highly dynamic VANET environment. Experimental results demonstrate that the proposed scheme significantly outperforms the existing methods in terms of both privacy protection and computational efficiency, offering a practical solution for the deployment of FL in vehicular network environments.
WENJ, ZHANGZ X, LANY,et al. A survey on federated learning:challenges and applications[J]. International Journal of Machine Learning and Cybernetics, 2023, 14(2): 513-535.
[2]
SHARMAS, GULERIAK. A comprehensive review on federated learning based models for healthcare applications[J]. Artificial Intelligence in Medicine,2023,146: 102691.
[3]
BYUNS, SARKERA, CHANGS Y,et al .Secure aggregation for privacy-preserving federated learning in vehicular networks[J].ACM Journal on Autonomous Transportation Systems,2024,1(3):1-25.
[4]
CHELLAPANDIV P, YUANL Q, BRINTONC G,et al .Federated learning for connected and automated vehicles:a survey of existing approaches and challenges[J].IEEE Transactions on Intelligent Vehicles,2024,9(1):119-137.
[5]
WANGC N, CHENX, WANGJ Z,et al .ATPFL:automatic trajectory prediction model design under federated learning framework[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),June 18-24,2022,New Orleans,LA,USA. IEEE, 2022: 6553-6562.
[6]
ALI W, DINI U, ALMOGRENA,et al .Federated learning-based privacy-aware location prediction model for Internet of vehicular things[J]. IEEE Transactions on Vehicular Technology,2025,74(2): 1968-1978.
CHEL, XUM S, CUIQ S .Federated learning based coordinated training method of a short-term load forecasting model[J].Journal of Hunan University (Natural Sciences),2022,49(8):117-127.(in Chinese)
[9]
FENGX, LIUH Y, YANGH W,et al .Batch-aggregate:efficient aggregation for private federated learning in VANETs[J]. IEEE Transactions on Dependable and Secure Computing, 2024, 21(5): 4939-4952.
[10]
QUZ G, TANGY, MUHAMMADG,et al .Privacy protection in intelligent vehicle networking:a novel federated learning algorithm based on information fusion[J]. Information Fusion,2023,98:101824.
WANGH, HUANGX G, LIF G .Secure federated learning based on secret sharing and aggregate signature[J]. Journal of Cryptologic Research, 2023, 10(3):588-596.(in Chinese)
LUJ, XIAOQ, GONGG J,et al .Federated learning distribution area data anomaly recognition based on dynamic differential privacy[J].Power System Technology,2025,49(8):3512-3521.(in Chinese)
[15]
GUOX J, LIUZ L, LIJ,et al .VeriFL:communication-efficient and fast verifiable aggregation for federated learning[J].IEEE Transactions on Information Forensics and Security,2021,16:1736-1751.
[16]
CAIY X, DINGW X, XIAOY X,et al .SecFed:a secure and efficient federated learning based on multi-key homomorphic encryption[J].IEEE Transactions on Dependable and Secure Computing,2024,21(4):3817-3833.
[17]
ZHANGJ L, LIUY, WUD,et al. VPFL:a verifiable privacy-preserving federated learning scheme for edge computing systems[J]. Digital Communications and Networks,2023, 9(4):981-989.
[18]
LIUB Y, LIUX W, GAOS,et al .Federated learning for VANET based on homomorphic encryption[C]//2023 Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC),November 10-13, 2023, Guilin, China. IEEE,2024:1-3.
[19]
ZHOUJ, HUJ L, XUEJ J,et al .Secure fair aggregation based on category grouping in federated learning[J].Information Fusion,2025,117:102838.
[20]
WANGH W, WANGL L, ZHANGK,et al .A conditional privacy-preserving certificateless aggregate signature scheme in the standard model for VANETs[J].IEEE Access,2022,10:15605-15618.
[21]
LIUJ W, ZHANGJ, AHMADJAN M,et al .A comprehensive privacy-preserving federated learning scheme with secure authentication and aggregation for Internet of medical things[J].IEEE Journal of Biomedical and Health Informatics,2024,28(6):3282-3292.
[22]
IQBALA, ZUBAIRM, KHANM A,et al .An efficient and secure certificateless aggregate signature scheme for vehicular ad hoc networks[J].Future Internet,2023,15(8):266.
[23]
LIG L, ZHAOY Y, LIY .CATFL:certificateless authentication-based trustworthy federated learning for 6G semantic communications[C]//2023 IEEE Wireless Communications and Networking Conference (WCNC), March 26-29,2023,Glasgow,United Kingdom. IEEE,2023:1-6.
[24]
WANGZ H, WANGH F, WANGY J,et al .CLASRM:a lightweight and secure certificateless aggregate signature scheme with revocation mechanism for 5G-enabled vehicular networks[J].Wireless Communications and Mobile Computing,2022,2022(1):3646960.
[25]
GUOR, DONGR H, LIX,et al .DRCLAS:an efficient certificateless aggregate signature scheme with dynamic revocation in vehicular ad-hoc networks[J].Vehicular Communications,2024,47:100763.
[26]
YUANX H, LIUJ Q, WANGB,et al. FedComm:a privacy-enhanced and efficient authentication protocol for federated learning in vehicular ad-hoc networks[J]. IEEE Transactions on Information Forensics and Security,2024,19:777-792.
[27]
FANGH K, QIANQ. Privacy preserving machine learning with homomorphic encryption and federated learning[J]. Future Internet, 2021, 13(4): 94.
[28]
YUT H, KUMARS, GUPTAA,et al.Gradient surgery for multi-task learning[EB/OL].(2020-01-19)
[29]
XIONGH, CHENJ H, MEIQ,et al .Conditional privacy-preserving authentication protocol with dynamic membership updating for VANETs[J].IEEE Transactions on Dependable and Secure Computing,2022,19(3): 2089-2104.
基金资助
国家自然科学基金资助项目(62461032)
National Natural ScienceFoundation of China(62461032)
甘肃省科技计划(22JR5RA158)
甘肃省科技计划(22JR5RA350)
Gansu Province Science and Technology Plan(22JR5RA158)
Gansu Province Science and Technology Plan(22JR5RA350)
甘肃省高校教师创新基金项目(2023A-041)
甘肃省高校教师创新基金项目(2023-ZD-234)
Gansu Province University Teachers Innovation Fund Project(2023A-041)
Gansu Province University Teachers Innovation Fund Project(2023-ZD-234)
兰州交通大学-天津大学联合创新基金(LH2024003)
Lanzhou Jiaotong University-Tianjin University Joint Innovation Fund Project(LH2024003)
甘肃省教育科技创新项目(2026B-266)
Gansu Provincial Education, Science and Technology Innovation Project(2026B-266)