EUVIMEDEUVIMED entdecken
Crossref

A Multi-Task Adversarial Attack against Face Authentication

Hanrui Wang, Shuo Wang, Cunjian Chen, Massimo Tistarelli, Zhe Jin

ACM Transactions on Multimedia Computing, Communications, and Applications · 30.11.2024 · 20 (11) · 1-24

DOI: 10.1145/3665496 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 07.11.2024. Verfasst von Hanrui Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: JSPS KAKENHI, JST CREST, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning-based identity management systems, such as face authentication systems, are vulnerable to adversarial attacks. However, existing attacks are typically designed for single-task purposes, which means they are tailored to exploit vulnerabilities unique to the individual target rather than being adaptable for multiple users or systems. This limitation makes them unsuitable for certain attack scenarios, such as morphing, universal, transferable, and counterattacks. In this article, we propose a multi-task adversarial attack algorithm called MTADV that are adaptable for multiple users or systems. By interpreting these scenarios as multi-task attacks, MTADV is applicable to both single- and multi-task attacks, and feasible in the white- and gray-box settings. Furthermore, MTADV is effective against various face datasets, including LFW, CelebA, and CelebA-HQ, and can work with different deep learning models, such as FaceNet, InsightFace, and CurricularFace. Importantly, MTADV retains its feasibility as a single-task attack targeting a single user/system. To the best of our knowledge, MTADV is the first adversarial attack method that can target all of the aforementioned scenarios in one algorithm.

Förderung

  • JSPS KAKENHI
  • JST CREST
  • National Natural Science Foundation of China
  • Anhui Provincial Natural Science Foundation
  • Faculty Initiatives Research, Monash University
  • e.INS-Ecosystem of Innovation for Next Generation Sardinia

Zitieren

APA

Wang, H., Wang, S., Chen, C., Tistarelli, M., & Jin, Z. (2024). A Multi-Task Adversarial Attack against Face Authentication. ACM Transactions on Multimedia Computing, Communications, and Applications, 20(11), 1-24. https://doi.org/10.1145/3665496

Vancouver

Wang H, Wang S, Chen C, Tistarelli M, Jin Z. A Multi-Task Adversarial Attack against Face Authentication. ACM Transactions on Multimedia Computing, Communications, and Applications. 2024;20(11):1-24. doi:10.1145/3665496

BibTeX
@article{Wang2024,
  author = {Wang, Hanrui and Wang, Shuo and Chen, Cunjian and Tistarelli, Massimo and Jin, Zhe},
  title = {A Multi-Task Adversarial Attack against Face Authentication},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2024},
  volume = {20},
  number = {11},
  pages = {1--24},
  doi = {10.1145/3665496}
}
Kostenlos starten →