论文标题
通过频率攻击来提高3D对抗攻击
Boosting 3D Adversarial Attacks with Attacking On Frequency
论文作者
论文摘要
深度神经网络（DNN）已被证明容易受到对抗攻击的影响。最近，3D对抗性攻击，尤其是对点云的对抗性攻击引起了人们的兴趣。但是，通过以前的方法获得的对抗点云显示出较弱的可传递性，并且易于防御。为了解决这些问题，在本文中，我们提出了一种新颖的点云攻击（称为AOF），该攻击更加注意点云的低频组成部分。我们将点云及其低频组件的损失结合在一起，以制作对抗样本。广泛的实验验证了AOF可以显着提高与最新（SOTA）攻击相比的可转移性，并且对SOTA 3D防御方法更强大。否则，与清洁点云相比，由AOF获得的对抗点云包含的变形比离群值更多。
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.
