EUVIMEDEUVIMED entdecken
Crossref

Curvature-Invariant Adversarial Attacks for 3D Point Clouds

Jianping Zhang, Wenwei Gu, Yizhan Huang, Zhihan Jiang, Weibin Wu, Michael R. Lyu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 7142-7150

DOI: 10.1609/aaai.v38i7.28542 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jianping Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Imperceptibility is one of the crucial requirements for adversarial examples. Previous adversarial attacks on 3D point cloud recognition suffer from noticeable outliers, resulting in low imperceptibility. We think that the drawbacks can be alleviated via taking the local curvature of the point cloud into consideration. Existing approaches introduce the local geometry distance into the attack objective function. However, their definition of the local geometry distance neglects different perceptibility of distortions along different directions. In this paper, we aim to enhance the imperceptibility of adversarial attacks on 3D point cloud recognition by better preserving the local curvature of the original 3D point clouds. To this end, we propose the Curvature-Invariant Method (CIM), which directly regularizes the back-propagated gradient during the generation of adversarial point clouds based on two assumptions. Specifically, we first decompose the back-propagated gradients into the tangent plane and the normal direction. Then we directly reduce the gradient along the large curvature direction on the tangent plane and only keep the gradient along the negative normal direction. Comprehensive experimental comparisons confirm the superiority of our approach. Notably, our strategy can achieve 7.2% and 14.5% improvements in Hausdorff distance and Gaussian curvature measurements of the imperceptibility.

Zitieren

APA

Zhang, J., Gu, W., Huang, Y., Jiang, Z., Wu, W., & Lyu, M. R. (2024). Curvature-Invariant Adversarial Attacks for 3D Point Clouds. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7142-7150. https://doi.org/10.1609/aaai.v38i7.28542

Vancouver

Zhang J, Gu W, Huang Y, Jiang Z, Wu W, Lyu MR. Curvature-Invariant Adversarial Attacks for 3D Point Clouds. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):7142-7150. doi:10.1609/aaai.v38i7.28542

BibTeX
@article{Zhang2024,
  author = {Zhang, Jianping and Gu, Wenwei and Huang, Yizhan and Jiang, Zhihan and Wu, Weibin and Lyu, Michael R.},
  title = {Curvature-Invariant Adversarial Attacks for 3D Point Clouds},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {7},
  pages = {7142--7150},
  doi = {10.1609/aaai.v38i7.28542}
}
Kostenlos starten →