Active Adversarial Noise Suppression for Image Forgery Localization
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-06 · 48 (6) · 6437-6451
DOI: 10.1109/tpami.2026.3656742 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-06. Verfasst von Rongxuan Peng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: NSFC, A*STAR, OTS Research Programme.
Abstract (Originalsprache)
Recent advances in deep learning have significantly propelled the development of image forgery localization. However, existing models remain highly vulnerable to adversarial attacks: imperceptible noise added to forged images can severely mislead these models. In this paper, we address this challenge with an Adversarial Noise Suppression Module (ANSM) that generates a defensive perturbation to suppress the attack effect of adversarial noise. We observe that forgery-relevant features extracted from adversarial and original forged images exhibit distinct distributions. To bridge this gap, we introduce Forgery-relevant Features Alignment (FFA) as a first-stage training strategy, which reduces distributional discrepancies by minimizing the channel-wise Kullback-Leibler divergence between these features. To further refine the defensive perturbation, we design a second-stage training strategy, termed Mask-guided Refinement (MgR), which incorporates a dual-mask constraint. MgR ensures that the defensive perturbation remains effective for both adversarial and original forged images, recovering forgery localization accuracy to their original level. Extensive experiments across various attack algorithms demonstrate that our method significantly restores the forgery localization model's performance on adversarial images. Notably, when ANSM is applied to original forged images, the performance remains nearly unaffected. To our best knowledge, this is the first report of adversarial defense in image forgery localization tasks.
Förderung
- NSFC
- A*STAR
- OTS Research Programme
- Guangdong Provincial Key Laboratory
Zitieren
APA
Peng, R., Tan, S., Mo, X., Kot, A. C., & Huang, J. (2026). Active Adversarial Noise Suppression for Image Forgery Localization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(6), 6437-6451. https://doi.org/10.1109/tpami.2026.3656742
Vancouver
Peng R, Tan S, Mo X, Kot AC, Huang J. Active Adversarial Noise Suppression for Image Forgery Localization. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(6):6437-6451. doi:10.1109/tpami.2026.3656742
BibTeX
@article{Peng2026,
author = {Peng, Rongxuan and Tan, Shunquan and Mo, Xianbo and Kot, Alex C and Huang, Jiwu},
title = {Active Adversarial Noise Suppression for Image Forgery Localization},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {6},
pages = {6437--6451},
doi = {10.1109/tpami.2026.3656742}
}
EUVIMED