Boosting Targeted Adversarial Transferability with Feature Contrastive Optimization
ACM Transactions on Multimedia Computing, Communications, and Applications · 30.06.2026 · 22 (6) · 1-21
DOI: 10.1145/3811823 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 21.05.2026. Verfasst von Jingtian Wang und 5 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jinan “New 20 Universities”–Project of Introducing Innovation Team, Qilu University of Technology.
Abstract (Originalsprache)
Transferable adversarial examples (AEs) have attracted considerable attention due to their ability to expose vulnerabilities in black-box deep neural networks (DNNs). However, achieving superior transferability for targeted attacks remains a challenge. In this article, inspired by the observation that AEs with smaller intra-class distances and larger inter-class distances tend to exhibit higher transferability, we propose a novel targeted attack based on Feature Contrastive Optimization (FCO). This attack enhances adversarial transferability by minimizing intra-class distances and maximizing inter-class distances. Specifically, we first define positive samples (belonging to the target class) and negative samples (belonging to non-target classes) that correspond to targeted AEs. Subsequently, leveraging these defined positive and negative samples, we propose two metrics—Intra-class Compactness (IC) and Inter-class Separability (IS)—to construct a novel Feature Contrastive (FC) loss. By integrating this plug-and-play FC loss into standard adversarial objectives, the generated AEs are encouraged to better align with the target class distribution while diverging from those of non-target classes. Extensive experiments on the ImageNet-compatible dataset demonstrate that our approach consistently improves targeted transferability across a broad range of DNN architectures.
Förderung
- National Natural Science Foundation of China
- Jinan “New 20 Universities”–Project of Introducing Innovation Team
- Qilu University of Technology
- Ministry of Finance, PR China
Zitieren
APA
Wang, J., Li, X., Li, J., Ma, B., Zhao, Y., & Zeng, J. (2026). Boosting Targeted Adversarial Transferability with Feature Contrastive Optimization. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(6), 1-21. https://doi.org/10.1145/3811823
Vancouver
Wang J, Li X, Li J, Ma B, Zhao Y, Zeng J. Boosting Targeted Adversarial Transferability with Feature Contrastive Optimization. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(6):1-21. doi:10.1145/3811823
BibTeX
@article{Wang2026,
author = {Wang, Jingtian and Li, Xiaolong and Li, Jian and Ma, Bin and Zhao, Yao and Zeng, Jinhua},
title = {Boosting Targeted Adversarial Transferability with Feature Contrastive Optimization},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2026},
volume = {22},
number = {6},
pages = {1--21},
doi = {10.1145/3811823}
}
EUVIMED