FPAD: Fuzzy-Prototype-Guided Adversarial Attack and Defense for Deep Cross-Modal Hashing
IEEE Transactions on Circuits and Systems for Video Technology · 2026-02 · 36 (2) · 2568-2580
DOI: 10.1109/tcsvt.2025.3604033 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-02. Verfasst von Zhongqing Yu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Science Foundation of China, National Science Foundation of Fujian Province, National Science Foundation of Xiamen City.
Abstract (Originalsprache)
Deep cross-modal hashing models generally inherit the vulnerabilities of deep neural networks, making them susceptible to adversarial attacks and thus posing a serious security risk during real-world deployment. Current adversarial attack or defense strategies often establish a weak correlation between the hashing codes and the targeted semantic representations, and there is still a lack of related works that simultaneously consider the attack and defense for deep cross-modal hashing. To alleviate these concerns, we propose a Fuzzy-Prototype-guided Adversarial Attack and Defense (FPAD) framework to enhance the adversarial robustness of deep cross-modal hashing models. First, an adaptive fuzzy-prototype learning network (FpNet) is efficiently presented to extract a set of fuzzy-prototypes, aiming to encode the underlying semantic structure of the heterogeneous modalities in both feature and Hamming spaces. Then, these derived prototypical hash codes are heuristically employed to supervise the generation of high-quality adversarial examples, while a fuzzy-prototype rectification scheme is simultaneously designed to preserve the latent semantic consistency between the adversarial and benign examples. By mixing the adversarial samples with the original training samples as the augmented inputs, an efficient fuzzy-prototype-guided adversarial learning framework is proposed to execute the collaborative adversarial training and generate robust cross-modal hash codes with high adversarial defense capabilities, therefore resisting various attacks and benefiting various challenging cross-modal hashing tasks. Extensive experiments evaluated on benchmark datasets show that the proposed FPAD framework not only produces high-quality adversarial samples to enhance the adversarial training process, but also shows its high adversarial defense capability to benefit various cross-modal hashing tasks. The code is available at: https://github.com/yzq131/FPAD
Förderung
- National Science Foundation of China
- National Science Foundation of Fujian Province
- National Science Foundation of Xiamen City
- Research Grants Council (RGC) Senior Research Fellow Scheme
Zitieren
APA
Yu, Z., Liu, X., Cheung, Y., Zhu, L., Xu, X., & Wang, N. (2026). FPAD: Fuzzy-Prototype-Guided Adversarial Attack and Defense for Deep Cross-Modal Hashing. IEEE Transactions on Circuits and Systems for Video Technology, 36(2), 2568-2580. https://doi.org/10.1109/tcsvt.2025.3604033
Vancouver
Yu Z, Liu X, Cheung Y, Zhu L, Xu X, Wang N. FPAD: Fuzzy-Prototype-Guided Adversarial Attack and Defense for Deep Cross-Modal Hashing. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(2):2568-2580. doi:10.1109/tcsvt.2025.3604033
BibTeX
@article{Yu2026,
author = {Yu, Zhongqing and Liu, Xin and Cheung, Yiu-Ming and Zhu, Lei and Xu, Xing and Wang, Nannan},
title = {FPAD: Fuzzy-Prototype-Guided Adversarial Attack and Defense for Deep Cross-Modal Hashing},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {2},
pages = {2568--2580},
doi = {10.1109/tcsvt.2025.3604033}
}
EUVIMED