2024/06/01 by Chengzeng You, You, Chengzeng, Zhongyuan Hau +5
Computer Science · Engineering · #Advanced Optical Imaging Technologies #Adversarial system #Artificial intelligence #Computer graphics (images) #Computer science #Computer vision #Geology #Human–computer interaction #Industrial Vision Systems and Defect Detection #Physical Unclonable Functions (PUFs) and Hardware Security
paper · pdf · doi:10.48550/arxiv.2406.00282
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
LiDAR sensors are widely used in autonomous vehicles to better perceive the environment. However, prior works have shown that LiDAR signals can be spoofed to hide real objects from 3D object detectors. This study explores the feasibility of reducing the required spoofing area through a novel object-hiding strategy based on virtual patches (VPs). We first manually design VPs (MVPs) and show that VP-focused attacks can achieve similar success rates with prior work but with a fraction of the required spoofing area. Then we design a framework Saliency-LiDAR (SALL), which can identify critical regions for LiDAR objects using Integrated Gradients. VPs crafted on critical regions (CVPs) reduce object detection recall by at least 15% compared to our baseline with an approximate 50% reduction in the spoofing area for vehicles of average size.