EUVIMEDEUVIMED entdecken
Crossref

A Survey of Robustness and Safety of 2D and 3D Deep Learning Models against Adversarial Attacks

Yanjie Li, Bin Xie, Songtao Guo, Yuanyuan Yang, Bin Xiao

ACM Computing Surveys · 30.06.2024 · 56 (6) · 1-37

DOI: 10.1145/3636551 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 22.01.2024. Verfasst von Yanjie Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 178 Literaturangaben. Gefördert von: HK RGC GRF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are not trustworthy enough because of their limited robustness against adversarial attacks. The physically realizable adversarial attacks further pose fatal threats to the application and human safety. Lots of papers have emerged to investigate the robustness and safety of deep learning models against adversarial attacks. To lead to trustworthy AI, we first construct a general threat model from different perspectives and then comprehensively review the latest progress of both 2D and 3D adversarial attacks. We extend the concept of adversarial examples beyond imperceptive perturbations and collate over 170 papers to give an overview of deep learning model robustness against various adversarial attacks. To the best of our knowledge, we are the first to systematically investigate adversarial attacks for 3D models, a flourishing field applied to many real-world applications. In addition, we examine physical adversarial attacks that lead to safety violations. Last but not least, we summarize present popular topics, give insights on challenges, and shed light on future research on trustworthy AI.

Förderung

  • HK RGC GRF

Zitieren

APA

Li, Y., Xie, B., Guo, S., Yang, Y., & Xiao, B. (2024). A Survey of Robustness and Safety of 2D and 3D Deep Learning Models against Adversarial Attacks. ACM Computing Surveys, 56(6), 1-37. https://doi.org/10.1145/3636551

Vancouver

Li Y, Xie B, Guo S, Yang Y, Xiao B. A Survey of Robustness and Safety of 2D and 3D Deep Learning Models against Adversarial Attacks. ACM Computing Surveys. 2024;56(6):1-37. doi:10.1145/3636551

BibTeX
@article{Li2024,
  author = {Li, Yanjie and Xie, Bin and Guo, Songtao and Yang, Yuanyuan and Xiao, Bin},
  title = {A Survey of Robustness and Safety of 2D and 3D Deep Learning Models against Adversarial Attacks},
  journal = {ACM Computing Surveys},
  year = {2024},
  volume = {56},
  number = {6},
  pages = {1--37},
  doi = {10.1145/3636551}
}
Kostenlos starten →