LiDAttack: Robust Black-box Attack on LiDAR-based Object Detection
This addresses security risks in autonomous driving systems by demonstrating a stealthy attack method, though it is incremental as it builds on existing adversarial attack research.
The paper tackles the vulnerability of LiDAR-based object detection to adversarial attacks by introducing LiDAttack, a robust black-box method that achieves up to 90% attack success rate on multiple datasets and models.
Since DNN is vulnerable to carefully crafted adversarial examples, adversarial attack on LiDAR sensors have been extensively studied. We introduce a robust black-box attack dubbed LiDAttack. It utilizes a genetic algorithm with a simulated annealing strategy to strictly limit the location and number of perturbation points, achieving a stealthy and effective attack. And it simulates scanning deviations, allowing it to adapt to dynamic changes in real world scenario variations. Extensive experiments are conducted on 3 datasets (i.e., KITTI, nuScenes, and self-constructed data) with 3 dominant object detection models (i.e., PointRCNN, PointPillar, and PV-RCNN++). The results reveal the efficiency of the LiDAttack when targeting a wide range of object detection models, with an attack success rate (ASR) up to 90%.