Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds

• Published in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 24326 - 24335
• Main Authors: Lou, Tianrui, Jia, Xiaojun, Gu, Jindong, Liu, Li, Liang, Siyuan, He, Bangyan, Cao, Xiaochun
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.06.2024
• Subjects: Computational modeling; Computer vision; Deformation; Perturbation methods; Point cloud compression; Solid modeling; Three-dimensional displays
• ISSN: 2575-7075
• DOI: 10.1109/CVPR52733.2024.02296

Adversarial attack methods based on point manipulation for 3D point cloud classification have revealed the fragility of 3D models, yet the adversarial examples they produce are easily perceived or defended against. The tradeoff between the imperceptibility and adversarial strength leads most point attack methods to inevitably introduce easily detectable outlier points upon a successful attack. An-other promising strategy, shape-based attack, can effectively eliminate outliers, but existing methods often suffer significant reductions in imperceptibility due to irrational deformations. We find that concealing deformation perturbations in areas insensitive to human eyes can achieve a better tradeoff between imperceptibility and adversarial strength, specifically in parts of the object surface that are complex and exhibit drastic curvature changes. Therefore, we propose a novel shape-based adversarial attack method, HiT-ADV, which initially conducts a two-stage search for attack regions based on saliency and imperceptibility scores, and then adds deformation perturbations in each attack region using Gaussian kernel functions. Additionally, HiT-ADV is extendable to physical attack. We propose that by employing benign resampling and benign rigid transformations, we can further enhance physical adversarial strength with little sacrifice to imperceptibility. Extensive experiments have validated the superiority of our method in terms of adversarial and imperceptible properties in both digital and physical spaces. Our code is avaliable at: https://github.com/TRLou/HiT-ADV.