We develop an extensible platform for exploring cyber-attacks on connected and autonomous vehicle (CAV) platoon controllers. A unique feature of our platform is the ability to address a large spectrum of cyber threats, including new attacks designed after deployment. This platform facilitates systematic exploration of cyber-attacks, helping to uncover real-time vulnerabilities across different designs of platoon controllers. Additionally, we introduce a novel, dual-stage detection mechanism that employs a time-series machine learning (ML) model for the real-time detection of attacks on the perception channels of a Model Predictive Control (MPC)-based CAV platoon. We present extensive experimental results to showcase the effectiveness and feasibility of our approach.
Exploration and Detection of Cyber-Attacks on MPC-Based Vehicular Platoons
2024-09-24
2661928 byte
Conference paper
Electronic Resource
English
AttentionGuard: Transformer-based Misbehavior Detection for Secure Vehicular Platoons
ArXiv | 2025
|Secure virtual coupling control of connected train platoons under cyber attacks
Taylor & Francis Verlag | 2025
|