Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving

Abstract

In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environment. Due to its direct impact on road safety, multiple prior efforts have been made to study its the security of perception systems. In contrast to prior work that concentrates on camera-based perception, in this work we perform the first security study of LiDAR-based perception in AV settings, which is highly important but unexplored. We consider LiDAR spoofing attacks as the threat model and set the attack goal as spoofing obstacles close to the front of a victim AV. We find that blindly applying LiDAR spoofing is insufficient to achieve this goal due to the machine learning-based object detection process. Thus, we then explore the possibility of strategically controlling the spoofed attack to fool the machine learning model. We formulate this task as an optimization problem and design modeling methods for the input perturbation function and the objective function. We also identify the inherent limitations of directly solving the problem using optimization and design an algorithm that combines optimization and global sampling, which improves the attack success rates to around 75%. As a case study to understand the attack impact at the AV driving decision level, we construct and evaluate two attack scenarios that may damage road safety and mobility. We also discuss defense directions at the AV system, sensor, and machine learning model levels.

arXiv commentAccepted at the ACM Conference on Computer and Communications Security (CCS), 2019

Cited by in corpus (21)

• Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
• DriveFuzz: Discovering Autonomous Driving Bugs through Driving Quality-Guided Fuzzing
• 3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection
• Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles
• Security and Privacy in the Emerging Cyber-Physical World: A Survey
• Towards robust sensing for Autonomous Vehicles: An adversarial perspective
• Safeguarding connected autonomous vehicle communication: Protocols, intra- and inter-vehicular attacks and defenses
• Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems
• Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perception
• Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks
• Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models
• Jacobian Regularization for Mitigating Universal Adversarial Perturbations
• Compensating for Sensing Failures via Delegation in Human-AI Hybrid Systems
• Optimizing Delegation in Collaborative Human-AI Hybrid Teams
• Adversarial Online Learning with Variable Plays in the Pursuit-Evasion Game: Theoretical Foundations and Application in Connected and Automated Vehicle Cybersecurity
• 3D Adversarial Augmentations for Robust Out-of-Domain Predictions
• Toward Certifying Maps for Safe Registration-based Localization Under Adverse Conditions
• Simulation of Sensor Spoofing Attacks on Unmanned Aerial Vehicles Using the Gazebo Simulator
• Quantum secured LiDAR with Gaussian modulated coherent states
• Hi-ALPS -- An Experimental Robustness Quantification of Six LiDAR-based Object Detection Systems for Autonomous Driving
• From bits to atoms: A survey of cross-layer safety in Embodied AI