Efficient Query-based Black-box Attack against Cross-modal Hashing Retrieval
ACM Transactions on Information Systems · 31.07.2023 · 41 (3) · 1-25
DOI: 10.1145/3559758 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 07.02.2023. Verfasst von Lei Zhu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong, China, Youth Innovation Project of Shandong Universities, China.
Abstract (Originalsprache)
Deep cross-modal hashing retrieval models inherit the vulnerability of deep neural networks. They are vulnerable to adversarial attacks, especially for the form of subtle perturbations to the inputs. Although many adversarial attack methods have been proposed to handle the robustness of hashing retrieval models, they still suffer from two problems: (1) Most of them are based on the white-box settings, which is usually unrealistic in practical application. (2) Iterative optimization for the generation of adversarial examples in them results in heavy computation. To address these problems, we propose an Efficient Query-based Black-Box Attack (EQB 2 A) against deep cross-modal hashing retrieval, which can efficiently generate adversarial examples for the black-box attack. Specifically, by sending a few query requests to the attacked retrieval system, the cross-modal retrieval model stealing is performed based on the neighbor relationship between the retrieved results and the query, thus obtaining the knockoffs to substitute the attacked system. A multi-modal knockoffs-driven adversarial generation is proposed to achieve efficient adversarial example generation. While the entire network training converges, EQB 2 A can efficiently generate adversarial examples by forward-propagation with only given benign images. Experiments show that EQB 2 A achieves superior attacking performance under the black-box setting.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong, China
- Youth Innovation Project of Shandong Universities, China
Zitieren
APA
Zhu, L., Wang, T., Li, J., Zhang, Z., Shen, J., & Wang, X. (2023). Efficient Query-based Black-box Attack against Cross-modal Hashing Retrieval. ACM Transactions on Information Systems, 41(3), 1-25. https://doi.org/10.1145/3559758
Vancouver
Zhu L, Wang T, Li J, Zhang Z, Shen J, Wang X. Efficient Query-based Black-box Attack against Cross-modal Hashing Retrieval. ACM Transactions on Information Systems. 2023;41(3):1-25. doi:10.1145/3559758
BibTeX
@article{Zhu2023,
author = {Zhu, Lei and Wang, Tianshi and Li, Jingjing and Zhang, Zheng and Shen, Jialie and Wang, Xinhua},
title = {Efficient Query-based Black-box Attack against Cross-modal Hashing Retrieval},
journal = {ACM Transactions on Information Systems},
year = {2023},
volume = {41},
number = {3},
pages = {1--25},
doi = {10.1145/3559758}
}
EUVIMED