3D Adversarial Attacks Beyond Point Cloud

TL;DR

This paper introduces Mesh Attack, a novel 3D adversarial attack method that directly perturbs mesh representations of objects, outperforming existing point cloud-based attacks and maintaining effectiveness under defenses.

Contribution

The paper proposes a differentiable sampling module and mesh-specific loss functions to enable effective gradient-based adversarial attacks directly on 3D meshes.

Findings

Outperforms state-of-the-art 3D attacks significantly

Maintains high attack success under various defenses

Effective in physical scenario reproductions

Abstract

Recently, 3D deep learning models have been shown to be susceptible to adversarial attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks perform perturbation to 3D point clouds. To reproduce these attacks in the physical scenario, a generated adversarial 3D point cloud need to be reconstructed to mesh, which leads to a significant drop in its adversarial effect. In this paper, we propose a strong 3D adversarial attack named Mesh Attack to address this problem by directly performing perturbation on mesh of a 3D object. In order to take advantage of the most effective gradient-based attack, a differentiable sample module that back-propagate the gradient of point cloud to mesh is introduced. To further ensure the adversarial mesh examples without outlier and 3D printable, three mesh losses are adopted. Extensive experiments demonstrate that the proposed scheme outperforms SOTA 3D attacks by a significant margin. We also achieved SOTA performance under various defenses. Our code is available at: https://github.com/cuge1995/Mesh-Attack.