Navigating Threats: A Survey of Physical Adversarial Attacks on LiDAR Perception Systems in Autonomous Vehicles

TL;DR

A thorough review of the current research landscape on physical adversarial attacks targeting LiDAR-based perception systems, covering both single-modality and multi-modality contexts, identifies critical challenges and highlights gaps in existing attacks for LiDAR-based systems.

Abstract

Autonomous vehicles (AVs) rely heavily on LiDAR (Light Detection and Ranging) systems for accurate perception and navigation, providing high-resolution 3D environmental data that is crucial for object detection and classification. However, LiDAR systems are vulnerable to adversarial attacks, which pose significant challenges to the safety and robustness of AVs. This survey presents a thorough review of the current research landscape on physical adversarial attacks targeting LiDAR-based perception systems, covering both single-modality and multi-modality contexts. We categorize and analyze various attack types, including spoofing and physical adversarial object attacks, detailing their methodologies, impacts, and potential real-world implications. Through detailed case studies and analyses, we identify critical challenges and highlight gaps in existing attacks for LiDAR-based systems. Additionally, we propose future research directions to enhance the security and resilience of these systems, ultimately contributing to the safer deployment of autonomous vehicles.

Figures (23)

• Figure 1: Overview of an autonomous vehicle navigation system: key modules including perception, localization, planning, and control.
• Figure 2: Perception sensors employed in autonomous vehicles.
• Figure 3: Overview of multi-sensor fusion based AD perception design. (Figure adapted from cao2021).
• Figure 4: Comparison of Digital and Physical Attacks.
• Figure 5: Cascaded fusion in autonomous vehicke systems.