EUVIMEDEUVIMED entdecken
Crossref

Saliency Attack: Towards Imperceptible Black-box Adversarial Attack

Zeyu Dai, Shengcai Liu, Qing Li, Ke Tang

ACM Transactions on Intelligent Systems and Technology · 30.06.2023 · 14 (3) · 1-20

DOI: 10.1145/3582563 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, 2023-04. Verfasst von Zeyu Dai und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Program for Guangdong Introducing Innovative and Entrepreneurial Teams.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency. However, such performance is often accompanied by compromises in attack imperceptibility, hindering the practical use of these approaches. In this article, we propose to restrict the perturbations to a small salient region to generate adversarial examples that can hardly be perceived. This approach is readily compatible with many existing black-box attacks and can significantly improve their imperceptibility with little degradation in attack success rates. Furthermore, we propose the Saliency Attack, a new black-box attack aiming to refine the perturbations in the salient region to achieve even better imperceptibility. Extensive experiments show that compared to the state-of-the-art black-box attacks, our approach achieves much better imperceptibility scores, including most apparent distortion (MAD), L 0 and L 2 distances, and also obtains significantly better true success rate and effective query number judged by a human-like threshold on MAD. Importantly, the perturbations generated by our approach are interpretable to some extent. Finally, it is also demonstrated to be robust to different detection-based defenses.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Program for Guangdong Introducing Innovative and Entrepreneurial Teams
  • Hong Kong Research Grants Council under the General Research Fund

Zitieren

APA

Dai, Z., Liu, S., Li, Q., & Tang, K. (2023). Saliency Attack: Towards Imperceptible Black-box Adversarial Attack. ACM Transactions on Intelligent Systems and Technology, 14(3), 1-20. https://doi.org/10.1145/3582563

Vancouver

Dai Z, Liu S, Li Q, Tang K. Saliency Attack: Towards Imperceptible Black-box Adversarial Attack. ACM Transactions on Intelligent Systems and Technology. 2023;14(3):1-20. doi:10.1145/3582563

BibTeX
@article{Dai2023,
  author = {Dai, Zeyu and Liu, Shengcai and Li, Qing and Tang, Ke},
  title = {Saliency Attack: Towards Imperceptible Black-box Adversarial Attack},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2023},
  volume = {14},
  number = {3},
  pages = {1--20},
  doi = {10.1145/3582563}
}
Kostenlos starten →