With the development of the Internet of Vehicles (IoV), vehicle wireless communication poses serious cybersecurity challenges. Faulty information, such as fake vehicle positions and speeds sent by surrounding vehicles, could cause vehicle collisions, traffic jams, and even casualties. Additionally, private vehicle data leakages, such as vehicle trajectory and user account information, may damage user property and security. Therefore, achieving a cyberattack-defense scheme in the IoV system with faulty data saturation is necessary. This paper proposes a Federated Learning-based Vehicle Trajectory Prediction Algorithm against Cyberattacks (FL-TP) to address the above problems. The FL-TP is intensively trained and tested using a publicly available Vehicular Reference Misbehavior (VeReMi) dataset with five types of cyberattacks: constant, constant offset, random, random offset, and eventual stop. The results show that the proposed FL-TP algorithm can improve cyberattack detection and trajectory prediction by up to 6.99% and 54.86%, respectively, under the maximum cyberattack permeability scenarios compared with benchmark methods.

翻译：随着车联网的发展，车辆无线通信带来了严峻的网络安全挑战。由周围车辆发送的虚假车辆位置和速度等错误信息，可能导致车辆碰撞、交通拥堵甚至人员伤亡。此外，车辆轨迹和用户账户信息等私人车辆数据的泄露，可能损害用户财产与安全。因此，在车联网系统中实现具有错误数据饱和特征（译者注：此处指大量错误数据存在的场景）的网络攻击防御方案十分必要。本文提出一种基于联邦学习的抗网络攻击车辆轨迹预测算法（FL-TP）来解决上述问题。该算法利用公开的车辆参考异常行为（VeReMi）数据集进行密集训练与测试，该数据集包含五种网络攻击类型：恒定攻击、恒定偏移攻击、随机攻击、随机偏移攻击及最终停车攻击。结果表明，与基准方法相比，所提出的FL-TP算法在最大网络攻击渗透场景下，可将网络攻击检测性能提升高达6.99%，轨迹预测精度提升高达54.86%。