Transferable Adversarial Face Attack with Text Controlled Attribute
Wenyun Li, Zheng Zhang, Xiangyuan Lan, Dongmei Jiang

TL;DR
This paper introduces TCA$^2$, a novel method for generating realistic, text-guided adversarial face images that are highly transferable across different face recognition systems, enhancing impersonation attack capabilities.
Contribution
The paper presents a new text-controlled adversarial attack method using Style-GAN and augmentation strategies to improve transferability and control over face attributes.
Findings
High transferability of adversarial faces across models
Effective control of face attributes via natural language
Successful attacks on real-world face recognition systems
Abstract
Traditional adversarial attacks typically produce adversarial examples under norm-constrained conditions, whereas unrestricted adversarial examples are free-form with semantically meaningful perturbations. Current unrestricted adversarial impersonation attacks exhibit limited control over adversarial face attributes and often suffer from low transferability. In this paper, we propose a novel Text Controlled Attribute Attack (TCA) to generate photorealistic adversarial impersonation faces guided by natural language. Specifically, the category-level personal softmax vector is employed to precisely guide the impersonation attacks. Additionally, we propose both data and model augmentation strategies to achieve transferable attacks on unknown target models. Finally, a generative model, \textit{i.e}, Style-GAN, is utilized to synthesize impersonated faces with desired attributes.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Biometric Identification and Security
MethodsSoftmax
