AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds


Deep neural networks are vulnerable to adversarial attacks, in which imperceptible perturbations to their input lead to erroneous network predictions. This phenomenon has been extensively studied in the image domain, and only recently extended to 3D point clouds. In this work, we present novel data-driven adversarial attacks against 3D point cloud networks. We aim to address the following problems in current 3D point cloud adversarial attacks: they do not transfer well between different networks, and they are easy to defend against simple statistical methods. To this extent, we develop new point cloud attacks (we dub AdvPC) that exploit input data distributions. These attacks lead to perturbations that are resilient against current defenses while remaining highly transferable compared to state-of-the-art attacks. We test our attacks using four popular point cloud networks: PointNet, PointNet++ (MSG and SSG), and DGCNN. Our proposed attack enables an increase in the transferability of up to 20 points for some networks. It also increases the ability to break defenses of up to 23 points on ModelNet40 data.

[Under submission] Arxive