Robust Vision Systems for Connected and Autonomous Vehicles: Security Challenges and Attack Vectors

TL;DR

This work addresses the challenge of ensuring robust vision in Connected and Autonomous Vehicles (CAVs) to achieve Level-5 autonomy. It introduces a reference architecture for CAV vision systems (CAVVS) and a threat model to analyze attack surfaces across data, models, and inputs, along with their CIA implications. By cataloging attack vectors such as data poisoning, data exfiltration, model extraction, logic corruption, membership inference, side-channel leakage, evasion, and man-in-the-middle attacks, the paper connects these threats to atomic road events and real-world sensing conditions. The authors also illustrate the limitations of current perception through experimental simulations with a pre-trained Inception-V3 model, underscoring the need for robust defenses and secure design practices to enable practical Level-5 autonomy.

Abstract

This article investigates the robustness of vision systems in Connected and Autonomous Vehicles (CAVs), which is critical for developing Level-5 autonomous driving capabilities. Safe and reliable CAV navigation undeniably depends on robust vision systems that enable accurate detection of objects, lane markings, and traffic signage. We analyze the key sensors and vision components essential for CAV navigation to derive a reference architecture for CAV vision system (CAVVS). This reference architecture provides a basis for identifying potential attack surfaces of CAVVS. Subsequently, we elaborate on identified attack vectors targeting each attack surface, rigorously evaluating their implications for confidentiality, integrity, and availability (CIA). Our study provides a comprehensive understanding of attack vector dynamics in vision systems, which is crucial for formulating robust security measures that can uphold the principles of the CIA triad.

Figures (14)

• Figure 1: A typical connected and autonomous vehicle (Figure credit: ford2023argo)
• Figure 2: Visibility of camera mounted on a CAV kim2022safety. The field of view of a camera mounted on the CAV captures the lane markings, the lead vehicle, the rear tires of the leading vehicle, and the vanishing point.
• Figure 3: Illustration of FMCW radar technology used in autonomous driving, depicting the detection of objects with their corresponding relative ranges, velocities, and azimuth angles srivastav2023radars.
• Figure 4: Ultrasonic sensor uses echolocation for detecting proximity and slow speeds lim2018autonomous.
• Figure 5: Illustration of sensor data in CARLA Simulation beck2023automated. Top and middle image show the front-facing camera and rear-facing camera data. Bottom image shows the LiDAR and Radar data.