Experimental Evaluation of Security Attacks on Self-Driving Car Platforms
Cryptography and Security
Summary
The authors studied how different cyberattacks affect small, low-cost autonomous vehicles by testing five types of attacks on real hardware. They measured how these attacks changed the vehicle's steering, computing load, and response speed. Their results showed each attack type leaves a unique "fingerprint" across these measures, like different patterns of behavior. This method works for both digital attacks that mess with software data and physical attacks that trick the vehicle's sensors. The authors suggest their findings could help create smarter defenses that spot and respond to specific attack patterns.
Authors
Viet K. Nguyen, Nathan Lee, Mohammad Husain
Abstract
Deep learning-based perception pipelines in autonomous ground vehicles are vulnerable to both adversarial manipulation and network-layer disruption. We present a systematic, on-hardware experimental evaluation of five attack classes: FGSM, PGD, man-in-the-middle (MitM), denial-of-service (DoS), and phantom attacks on low-cost autonomous vehicle platforms (JetRacer and Yahboom). Using a standardized 13-second experimental protocol and comprehensive automated logging, we systematically characterize three dimensions of attack behavior:(i) control deviation, (ii) computational cost, and (iii) runtime responsiveness. Our analysis reveals that distinct attack classes produce consistent and separable "fingerprints" across these dimensions: perception attacks (MitM output manipulation and phantom projection) generate high steering deviation signatures with nominal computational overhead, PGD produces combined steering perturbation and computational load signatures across multiple dimensions, and DoS exhibits frame rate and latency degradation signatures with minimal control-plane perturbation. We demonstrate that our fingerprinting framework generalizes across both digital attacks (adversarial perturbations, network manipulation) and environmental attacks (projected false features), providing a foundation for attack-aware monitoring systems and targeted, signature-based defense mechanisms.