Diffusion Models for Imperceptible and Transferable Adversarial Attack
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-02 · 47 (2) · 961-977
DOI: 10.1109/tpami.2024.3480519 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-02. Verfasst von Jianqi Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 110-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Many existing adversarial attacks generate -norm perturbations on image RGB space. Despite some achievements in transferability and attack success rate, the crafted adversarial examples are easily perceived by human eyes. Towards visual imperceptibility, some recent works explore unrestricted attacks without -norm constraints, yet lacking transferability of attacking black-box models. In this work, we propose a novel imperceptible and transferable attack by leveraging both the generative and discriminative power of diffusion models. Specifically, instead of direct manipulation in pixel space, we craft perturbations in the latent space of diffusion models. Combined with well-designed content-preserving structures, we can generate human-insensitive perturbations embedded with semantic clues. For better transferability, we further "deceive" the diffusion model which can be viewed as an implicit recognition surrogate, by distracting its attention away from the target regions. To our knowledge, our proposed method, DiffAttack, is the first that introduces diffusion models into the adversarial attack field. Extensive experiments conducted across diverse model architectures (CNNs, Transformers, and MLPs), datasets (ImageNet, CUB-200, and Standford Cars), and defense mechanisms underscore the superiority of our attack over existing methods such as iterative attacks, GAN-based attacks, and ensemble attacks. Furthermore, we provide a comprehensive discussion on future research avenues in diffusion-based adversarial attacks, aiming to chart a course for this burgeoning field.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Beijing Natural Science Foundation
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Chen, J., Chen, H., Chen, K., Zhang, Y., Zou, Z., & Shi, Z. (2025). Diffusion Models for Imperceptible and Transferable Adversarial Attack. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(2), 961-977. https://doi.org/10.1109/tpami.2024.3480519
Vancouver
Chen J, Chen H, Chen K, Zhang Y, Zou Z, Shi Z. Diffusion Models for Imperceptible and Transferable Adversarial Attack. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(2):961-977. doi:10.1109/tpami.2024.3480519
BibTeX
@article{Chen2025,
author = {Chen, Jianqi and Chen, Hao and Chen, Keyan and Zhang, Yilan and Zou, Zhengxia and Shi, Zhenwei},
title = {Diffusion Models for Imperceptible and Transferable Adversarial Attack},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {2},
pages = {961--977},
doi = {10.1109/tpami.2024.3480519}
}
EUVIMED