EUVIMEDEUVIMED entdecken
Crossref

Towards Transferable Adversarial Attacks with Centralized Perturbation

Shangbo Wu, Yu-an Tan, Yajie Wang, Ruinan Ma, Wencong Ma, Yuanzhang Li

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 6109-6116

DOI: 10.1609/aaai.v38i6.28427 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Shangbo Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image, resulting in excessive noise that overfit the source model. Concentrating perturbation to dominant image regions that are model-agnostic is crucial to improving adversarial efficacy. However, limiting perturbation to local regions in the spatial domain proves inadequate in augmenting transferability. To this end, we propose a transferable adversarial attack with fine-grained perturbation optimization in the frequency domain, creating centralized perturbation. We devise a systematic pipeline to dynamically constrain perturbation optimization to dominant frequency coefficients. The constraint is optimized in parallel at each iteration, ensuring the directional alignment of perturbation optimization with model prediction. Our approach allows us to centralize perturbation towards sample-specific important frequency features, which are shared by DNNs, effectively mitigating source model overfitting. Experiments demonstrate that by dynamically centralizing perturbation on dominating frequency coefficients, crafted adversarial examples exhibit stronger transferability, and allowing them to bypass various defenses.

Zitieren

APA

Wu, S., Tan, Y., Wang, Y., Ma, R., Ma, W., & Li, Y. (2024). Towards Transferable Adversarial Attacks with Centralized Perturbation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6109-6116. https://doi.org/10.1609/aaai.v38i6.28427

Vancouver

Wu S, Tan Y, Wang Y, Ma R, Ma W, Li Y. Towards Transferable Adversarial Attacks with Centralized Perturbation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):6109-6116. doi:10.1609/aaai.v38i6.28427

BibTeX
@article{Wu2024,
  author = {Wu, Shangbo and Tan, Yu-an and Wang, Yajie and Ma, Ruinan and Ma, Wencong and Li, Yuanzhang},
  title = {Towards Transferable Adversarial Attacks with Centralized Perturbation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {6},
  pages = {6109--6116},
  doi = {10.1609/aaai.v38i6.28427}
}
Kostenlos starten →