3D Adversarial Attacks Beyond Point Cloud
This addresses the vulnerability of 3D deep learning models to adversarial attacks, particularly for applications requiring physical reconstruction, though it is incremental as it builds on existing gradient-based methods.
The paper tackles the problem of 3D adversarial attacks by proposing Mesh Attack, which directly perturbs meshes instead of point clouds to maintain effectiveness in physical scenarios, outperforming state-of-the-art methods by a significant margin and achieving top performance under various defenses.
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.