Adversarial 3D Virtual Patches using Integrated Gradients
This addresses security vulnerabilities in autonomous vehicle perception systems, representing an incremental improvement over prior spoofing methods.
The study tackled the problem of reducing the required spoofing area for hiding objects from LiDAR-based 3D object detectors in autonomous vehicles, achieving a 50% reduction in spoofing area while decreasing object detection recall by at least 15%.
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.