Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Efficient Query-based Black-box Attack against Cross-modal Hashing Retrieval

Efficient Query-based Black-box Attack against Cross-modal Hashing Retrieval 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 (EQB2A) 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, EQB2A can efficiently generate adversarial examples by forward-propagation with only given benign images. Experiments show that EQB2A achieves superior attacking performance under the black-box setting. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Information Systems (TOIS) Association for Computing Machinery

Efficient Query-based Black-box Attack against Cross-modal Hashing Retrieval

Loading next page...
 
/lp/association-for-computing-machinery/efficient-query-based-black-box-attack-against-cross-modal-hashing-QTCNHPUyoe

References (63)

Publisher
Association for Computing Machinery
Copyright
Copyright © 2023 Association for Computing Machinery.
ISSN
1046-8188
eISSN
1558-2868
DOI
10.1145/3559758
Publisher site
See Article on Publisher Site

Abstract

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 (EQB2A) 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, EQB2A can efficiently generate adversarial examples by forward-propagation with only given benign images. Experiments show that EQB2A achieves superior attacking performance under the black-box setting.

Journal

ACM Transactions on Information Systems (TOIS)Association for Computing Machinery

Published: Feb 7, 2023

Keywords: Adversarial attack

There are no references for this article.