Exploring Attack Resilience in Distributed Platoon Controllers with Model Predictive Control
This addresses safety risks in transportation systems from cyber-attacks on platoon controllers, but it is incremental as it builds on existing MPC and ML methods for a specific domain.
The paper tackled the vulnerability of distributed vehicle platoon controllers to cyber-attacks like MITM and FDI, simulating these attacks with MPC to identify weaknesses and proposing countermeasures including ML-based detection, which improved security and resilience.
The extensive use of distributed vehicle platoon controllers has resulted in several benefits for transportation systems, such as increased traffic flow, fuel efficiency, and decreased pollution. The rising reliance on interconnected systems and communication networks, on the other hand, exposes these controllers to potential cyber-attacks, which may compromise their safety and functionality. This thesis aims to improve the security of distributed vehicle platoon controllers by investigating attack scenarios and assessing their influence on system performance. Various attack techniques, including man-in-the-middle (MITM) and false data injection (FDI), are simulated using Model Predictive Control (MPC) controller to identify vulnerabilities and weaknesses of the platoon controller. Countermeasures are offered and tested, that includes attack analysis and reinforced communication protocols using Machine Learning techniques for detection. The findings emphasize the significance of integrating security issues into their design and implementation, which helps to construct safe and resilient distributed platoon controllers.