IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration

TL;DR

This paper introduces IF-Defense, a novel method that restores clean 3D point clouds from adversarially attacked ones by optimizing point coordinates with implicit functions, significantly improving robustness against various attacks.

Contribution

It proposes a geometry- and distribution-aware implicit function-based framework for defending 3D point clouds from adversarial attacks, achieving state-of-the-art results.

Findings

Achieves 20.02% improvement in classification accuracy against point dropping attack.

Achieves 16.29% improvement against LG-GAN attack.

Outperforms existing defenses on multiple 3D neural network models.

Abstract

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.