Enhanced Cyber-physical Security of Steering Stability Control System for Four-Wheel Independent Drive Electric Vehicles

In this paper, we present a residual-based anomaly detection method to enhance the cyber-physical security of the steering stability control system (SSCS) in a four-wheel independent drive electric vehicle. With the approach of the linear quadratic regulator, the SSCS is developed through the yaw moment generated by the torque deviation between the motors, the goal of which is to improve the lateral stability of the vehicle body. To prevent the vehicle against cyber-physical attacks, e.g., integrity attacks, we propose a residual-based anomaly detection method. Compared to traditional residual-based anomaly detection, the presented method can deal with threats on both control inputs and sensor measurements by combining physics-based and learning-based approaches. Simulation results have shown the effectiveness of the proposed detection method.