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 low-frequency 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.

翻译：最近,三维对抗性攻击,特别是点云的对抗性攻击,引起了越来越多的人的兴趣。然而,通过以往方法获得的对抗性云云的可转移性较弱,而且容易防御。为了解决这些问题,我们在本文件中建议采用新的点云攻击(dubbed AOF),对点云的低频部分给予更多的注意。我们把点云及其低频部分的损失与编造对抗性样品结合起来。广泛的实验证明,AOF可以大大改善可转移性,而与最先进的(SOTA)攻击相比,对SOTA 3D防御方法则更加强大。 否则,与清洁的云相比,AOF获得的对点云含有比外向更大的畸形。