Invisible Black-Box Backdoor Attack against Deep Cross-Modal Hashing Retrieval
ACM Transactions on Information Systems · 31.07.2024 · 42 (4) · 1-27
DOI: 10.1145/3650205 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 26.04.2024. Verfasst von Tianshi Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong, China, CCF-Baidu Open Fund.
Abstract (Originalsprache)
Deep cross-modal hashing has promoted the field of multi-modal retrieval due to its excellent efficiency and storage, but its vulnerability to backdoor attacks is rarely studied. Notably, current deep cross-modal hashing methods inevitably require large-scale training data, resulting in poisoned samples with imperceptible triggers that can easily be camouflaged into the training data to bury backdoors in the victim model. Nevertheless, existing backdoor attacks focus on the uni-modal vision domain, while the multi-modal gap and hash quantization weaken their attack performance. In addressing the aforementioned challenges, we undertake an invisible black-box backdoor attack against deep cross-modal hashing retrieval in this article. To the best of our knowledge, this is the first attempt in this research field. Specifically, we develop a flexible trigger generator to generate the attacker’s specified triggers, which learns the sample semantics of the non-poisoned modality to bridge the cross-modal attack gap. Then, we devise an input-aware injection network, which embeds the generated triggers into benign samples in the form of sample-specific stealth and realizes cross-modal semantic interaction between triggers and poisoned samples. Owing to the knowledge-agnostic of victim models, we enable any cross-modal hashing knockoff to facilitate the black-box backdoor attack and alleviate the attack weakening of hash quantization. Moreover, we propose a confusing perturbation and mask strategy to induce the high-performance victim models to focus on imperceptible triggers in poisoned samples. Extensive experiments on benchmark datasets demonstrate that our method has a state-of-the-art attack performance against deep cross-modal hashing retrieval. Besides, we investigate the influences of transferable attacks, few-shot poisoning, multi-modal poisoning, perceptibility, and potential defenses on backdoor attacks. Our codes and datasets are available at https://github.com/tswang0116/IB3A.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong, China
- CCF-Baidu Open Fund
Zitieren
APA
Wang, T., Li, F., Zhu, L., Li, J., Zhang, Z., & Shen, H. T. (2024). Invisible Black-Box Backdoor Attack against Deep Cross-Modal Hashing Retrieval. ACM Transactions on Information Systems, 42(4), 1-27. https://doi.org/10.1145/3650205
Vancouver
Wang T, Li F, Zhu L, Li J, Zhang Z, Shen HT. Invisible Black-Box Backdoor Attack against Deep Cross-Modal Hashing Retrieval. ACM Transactions on Information Systems. 2024;42(4):1-27. doi:10.1145/3650205
BibTeX
@article{Wang2024,
author = {Wang, Tianshi and Li, Fengling and Zhu, Lei and Li, Jingjing and Zhang, Zheng and Shen, Heng Tao},
title = {Invisible Black-Box Backdoor Attack against Deep Cross-Modal Hashing Retrieval},
journal = {ACM Transactions on Information Systems},
year = {2024},
volume = {42},
number = {4},
pages = {1--27},
doi = {10.1145/3650205}
}
EUVIMED