New Attack Detection Methods for Connected and Automated Vehicles

Abstract

Ensuring the security of Connected and Automated Vehicles (CAVs) against adversarial threats remains a critical challenge in cyber-physical systems. This thesis investigates attack detection methodologies and presents novel dual-perspective detection frameworks to enhance CAVs resilience. We first propose a vehicle dynamics-based attack detector that integrates the Unscented Kalman Filter (UKF) with machine learning techniques. This approach monitors physical system behaviour and identifies anomalies when sensor readings deviate from predicted states. Our enhanced model captures nonlinear vehicle dynamics while maintaining real-time performance, enabling the detection of sophisticated attacks that traditional linear models would miss. We develop a complementary trajectory-based detection framework that analyzes driving behaviour rationality to address the limitations of purely physics-based detection. This system evaluates vehicle trajectories within their environmental context, incorporating road conditions, traffic signals, and surrounding vehicle data. By leveraging neural networks for trajectory prediction and evaluation, our approach can identify malicious interventions even when attackers manipulate vehicle behaviour within physically plausible limits. Integrating these two detection perspectives—one based on vehicle dynamics modelling and the other on trajectory rationality analysis—provides a comprehensive security framework that significantly improves detection accuracy while reducing false positives. Experimental results demonstrate our system’s effectiveness against various attack vectors, including false data injection, adversarial control perturbations, and sensor spoofing attacks. Our research contributes to autonomous vehicle security by developing a holistic detection approach that considers both immediate physical anomalies and broader behavioural inconsistencies, enhancing system resilience against increasingly sophisticated cyber-physical threats.