EUVIMEDEUVIMED entdecken
Crossref

Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing

Daizong Liu, Wei Hu, Xin Li

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-05 · 46 (5) · 3079-3095

DOI: 10.1109/tpami.2023.3339130 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-05. Verfasst von Daizong Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 92 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the increasing attention in various 3D safety-critical applications, point cloud learning models have been shown to be vulnerable to adversarial attacks. Although existing 3D attack methods achieve high success rates, they delve into the data space with point-wise perturbation, which may neglect the geometric characteristics. Instead, we propose point cloud attacks from a new perspective-the graph spectral domain attack, aiming to perturb graph transform coefficients in the spectral domain that correspond to varying certain geometric structures. Specifically, leveraging on graph signal processing, we first adaptively transform the coordinates of points onto the spectral domain via graph Fourier transform (GFT) for compact representation. Then, we analyze the influence of different spectral bands on the geometric structure, based on which we propose to perturb the GFT coefficients via a learnable graph spectral filter. Considering the low-frequency components mainly contribute to the rough shape of the 3D object, we further introduce a low-frequency constraint to limit perturbations within imperceptible high-frequency components. Finally, the adversarial point cloud is generated by transforming the perturbed spectral representation back to the data domain via the inverse GFT. Experimental results demonstrate the effectiveness of the proposed attack in terms of both the imperceptibility and attack success rates.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, D., Hu, W., & Li, X. (2024). Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 3079-3095. https://doi.org/10.1109/tpami.2023.3339130

Vancouver

Liu D, Hu W, Li X. Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(5):3079-3095. doi:10.1109/tpami.2023.3339130

BibTeX
@article{Liu2024,
  author = {Liu, Daizong and Hu, Wei and Li, Xin},
  title = {Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {5},
  pages = {3079--3095},
  doi = {10.1109/tpami.2023.3339130}
}
Kostenlos starten →