Resilient Cooperative Adaptive Cruise Control for Autonomous Vehicles Using Machine Learning

TL;DR

This paper introduces RACCON, a machine learning-based system that enhances the resilience of cooperative adaptive cruise control in autonomous vehicles against malicious V2V communication attacks, ensuring safety and efficiency.

Contribution

The paper presents a novel resiliency infrastructure, RACCON, that detects and mitigates V2V attacks on CACC using on-board machine learning models for real-time response.

Findings

RACCON effectively detects V2V attacks in real-time.

Vehicles with RACCON maintain safety and efficiency under adversarial conditions.

Experimental results demonstrate RACCON's robustness and reliability.

Abstract

Cooperative Adaptive Cruise Control (CACC) is a fundamental connected vehicle application that extends Adaptive Cruise Control by exploiting vehicle-to-vehicle (V2V) communication. CACC is a crucial ingredient for numerous autonomous vehicle functionalities including platooning, distributed route management, etc. Unfortunately, malicious V2V communications can subvert CACC, leading to string instability and road accidents. In this paper, we develop a novel resiliency infrastructure, RACCON, for detecting and mitigating V2V attacks on CACC. RACCON uses machine learning to develop an on-board prediction model that captures anomalous vehicular responses and performs mitigation in real time. RACCON-enabled vehicles can exploit the high efficiency of CACC without compromising safety, even under potentially adversarial scenarios. We present extensive experimental evaluation to demonstrate the efficacy of RACCON.