Adversarial shape perturbations on 3D point clouds

TL;DR

This paper investigates how adversarial shape perturbations can deceive 3D point cloud neural networks, highlighting vulnerabilities and evaluating attack effectiveness against defenses in 3D shape recognition.

Contribution

It introduces and analyzes three novel shape attack methods on 3D point cloud classifiers, demonstrating their effectiveness even against existing defenses.

Findings

Some shape attacks bypass point-removal defenses

Distributional attacks involve imperceptible point perturbations

Shape attacks can deform point clouds to fool classifiers

Abstract

The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving. One commonly used 3D data type is 3D point clouds, which describe shape information. We examine the problem of creating robust models from the perspective of the attacker, which is necessary in understanding how 3D neural networks can be exploited. We explore two categories of attacks: distributional attacks that involve imperceptible perturbations to the distribution of points, and shape attacks that involve deforming the shape represented by a point cloud. We explore three possible shape attacks for attacking 3D point cloud classification and show that some of them are able to be effective even against preprocessing steps, like the previously proposed point-removal defenses.