3D-VFD: A Victim-free Detector against 3D Adversarial Point Clouds
This addresses security risks in 3D computer vision applications by providing a novel detection method that does not rely on the victim model, offering a practical solution for real-world deployment.
The paper tackles the vulnerability of 3D deep models to adversarial point clouds by proposing 3D-VFD, a victim-free detector that achieves state-of-the-art detection performance with fast speed, effectively identifying attacks based on point adding and perturbation.
3D deep models consuming point clouds have achieved sound application effects in computer vision. However, recent studies have shown they are vulnerable to 3D adversarial point clouds. In this paper, we regard these malicious point clouds as 3D steganography examples and present a new perspective, 3D steganalysis, to counter such examples. Specifically, we propose 3D-VFD, a victim-free detector against 3D adversarial point clouds. Its core idea is to capture the discrepancies between residual geometric feature distributions of benign point clouds and adversarial point clouds and map these point clouds to a lower dimensional space where we can efficiently distinguish them. Unlike existing detection techniques against 3D adversarial point clouds, 3D-VFD does not rely on the victim 3D deep model's outputs for discrimination. Extensive experiments demonstrate that 3D-VFD achieves state-of-the-art detection and can effectively detect 3D adversarial attacks based on point adding and point perturbation while keeping fast detection speed.