期刊
IEEE SENSORS JOURNAL
卷 22, 期 7, 页码 7385-7398出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2022.3153338
关键词
Protocols; Collaborative work; Authentication; Security; Sensors; Data models; Servers; Social Internet of Vehicles (SIoV); data security; federated learning; anonymous mutual authentication
资金
- National Natural Science Foundation of China [62071170, 62171180, 62072158]
- Program for Innovative Research Team in University of Henan Province [21IRTSTHN015]
- Key Science and Research Program in University of Henan Province [21A510001]
- Henan Province Science Fund for Distinguished Young Scholars [222300420006]
This paper proposes a collaborative authentication protocol for federated learning to protect the private data of vehicle clients and reduce data transmission delay in the Social Internet of Vehicles. By encrypting the parameters of the vehicle client model and implementing efficient anonymous mutual authentication and key agreement, the protocol effectively prevents data leakage and resolves overfitting of the globally aggregated model.
In the Social Internet of Vehicles (SIoV), federated learning is able to significantly protect the private data of the vehicle's client, while reducing the transmission load between entities. Nevertheless, data can still be stolen by an adversary who analyzes the parameters uploaded by the client to steal it. In this paper, to effectively prevent data leakage and reduce the propagation delay of data, we design a federated learning collaborative authentication protocol for shared data. The parameters of the vehicle client model are encrypted by the protocol in the federated learning. The vehicle and other entities of the protocol realize efficient anonymous mutual authentication and key agreement. The security of the proposed protocol is proved in the stochastic predictive machine model. The simulation results on the SUMO and OMNeT++ platforms show that the authentication delay is the lowest compared to other protocols and the packet loss rate is reduced to 4.68%. Moreover, the overfitting of the globally aggregated model is effectively resolved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据