EUVIMEDEUVIMED entdecken
Crossref

Once and for All: Universal Transferable Adversarial Perturbation against Deep Hashing-Based Facial Image Retrieval

Long Tang, Dengpan Ye, Yunna Lv, Chuanxi Chen, Yunming Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5136-5144

DOI: 10.1609/aaai.v38i6.28319 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Long Tang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep Hashing (DH)-based image retrieval has been widely applied to face-matching systems due to its accuracy and efficiency. However, this convenience comes with an increased risk of privacy leakage. DH models inherit the vulnerability to adversarial attacks, which can be used to prevent the retrieval of private images. Existing adversarial attacks against DH typically target a single image or a specific class of images, lacking universal adversarial perturbation for the entire hash dataset. In this paper, we propose the first universal transferable adversarial perturbation against DH-based facial image retrieval, a single perturbation can protect all images. Specifically, we explore the relationship between clusters learned by different DH models and define the optimization objective of universal perturbation as leaving from the overall hash center. To mitigate the challenge of single-objective optimization, we randomly obtain sub-cluster centers and further propose sub-task-based meta-learning to aid in overall optimization. We test our method with popular facial datasets and DH models, indicating impressive cross-image, -identity, -model, and -scheme universal anti-retrieval performance. Compared to state-of-the-art methods, our performance is competitive in white-box settings and exhibits significant improvements of 10%-70% in transferability in all black-box settings.

Zitieren

APA

Tang, L., Ye, D., Lv, Y., Chen, C., & Zhang, Y. (2024). Once and for All: Universal Transferable Adversarial Perturbation against Deep Hashing-Based Facial Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5136-5144. https://doi.org/10.1609/aaai.v38i6.28319

Vancouver

Tang L, Ye D, Lv Y, Chen C, Zhang Y. Once and for All: Universal Transferable Adversarial Perturbation against Deep Hashing-Based Facial Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5136-5144. doi:10.1609/aaai.v38i6.28319

BibTeX
@article{Tang2024,
  author = {Tang, Long and Ye, Dengpan and Lv, Yunna and Chen, Chuanxi and Zhang, Yunming},
  title = {Once and for All: Universal Transferable Adversarial Perturbation against Deep Hashing-Based Facial Image Retrieval},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {6},
  pages = {5136--5144},
  doi = {10.1609/aaai.v38i6.28319}
}
Kostenlos starten →