IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
This addresses security risks in 3D vision applications like autonomous driving and robotics, though it is incremental as it builds on existing defense methods.
The paper tackles the vulnerability of deep neural networks to 3D adversarial attacks on point clouds by proposing IF-Defense, a framework that restores clean point clouds from attacked ones, achieving state-of-the-art defense performance with improvements such as 20.02% in classification accuracy against salient point dropping attack on PointNet.
Point cloud is an important 3D data representation widely used in many essential applications. Leveraging deep neural networks, recent works have shown great success in processing 3D point clouds. However, those deep neural networks are vulnerable to various 3D adversarial attacks, which can be summarized as two primary types: point perturbation that affects local point distribution, and surface distortion that causes dramatic changes in geometry. In this paper, we simultaneously address both the aforementioned attacks by learning to restore the clean point clouds from the attacked ones. More specifically, we propose an IF-Defense framework to directly optimize the coordinates of input points with geometry-aware and distribution-aware constraints. The former aims to recover the surface of point cloud through implicit function, while the latter encourages evenly-distributed points. Our experimental results show that IF-Defense achieves the state-of-the-art defense performance against existing 3D adversarial attacks on PointNet, PointNet++, DGCNN, PointConv and RS-CNN. For example, compared with previous methods, IF-Defense presents 20.02% improvement in classification accuracy against salient point dropping attack and 16.29% against LG-GAN attack on PointNet. Our code is available at https://github.com/Wuziyi616/IF-Defense.