Choudhury, Tashfique Hasnine (University of Florida), DUAN, CHENGWEI (University of Florida), zhang, hanyu (University of Florida), Du, Lili (University of Florida), Ray, Sandip (University of Florida)

Exploration and Detection of Cyber-Attacks on MPC-Based Vehicular Platoons

Scheduled for presentation during the Regular Session "Advanced Vehicle Safety Systems II" (ThAT8), Thursday, September 26, 2024, 12:10−12:30, Salon 16

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 8, 2024

Abstract

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.