Boosting 3D Adversarial Attacks with Attacking On Frequency

Abstract

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a novel point cloud attack (dubbed AOF) that pays more attention on the low-frequency component of point clouds. We combine the losses from point cloud and its lowfrequency component to craft adversarial samples. Extensive experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks, and is more robust to SOTA 3D defense methods. Otherwise, compared to clean point clouds, adversarial point clouds obtained by AOF contain more deformation than outlier.

LPF-Defense: 3D Adversarial Defense based on Frequency Analysis

“…Only very recently, in 3D space, there is a parallel study [48] working on frequency domain in 3D adversarial attack methods. The work in [48] has suggested an adversarial attack based on the frequency domain when using DFT (graph-based). But our work proposes a defense method based on the frequency domain when using spherical harmonic transformation.…”