Boosting 3D Adversarial Attacks with Attacking On Frequency
This work addresses vulnerabilities in 3D deep neural networks for applications like autonomous driving or robotics, representing an incremental improvement over existing attacks.
The paper tackles the problem of weak transferability and easy defense of 3D adversarial attacks on point clouds by proposing AOF, a method that focuses on low-frequency components, resulting in significantly improved transferability and robustness against state-of-the-art defenses.
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.