Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition
This addresses security vulnerabilities in face recognition for applications like authentication, though it is an incremental advancement over existing adversarial attack methods.
The paper tackles the problem of adversarial attacks on face recognition systems by proposing Adv-Makeup, a method that generates imperceptible and transferable attacks, achieving significant improvements in attack success rates under black-box settings, including against commercial systems.
Deep neural networks, particularly face recognition models, have been shown to be vulnerable to both digital and physical adversarial examples. However, existing adversarial examples against face recognition systems either lack transferability to black-box models, or fail to be implemented in practice. In this paper, we propose a unified adversarial face generation method - Adv-Makeup, which can realize imperceptible and transferable attack under black-box setting. Adv-Makeup develops a task-driven makeup generation method with the blending module to synthesize imperceptible eye shadow over the orbital region on faces. And to achieve transferability, Adv-Makeup implements a fine-grained meta-learning adversarial attack strategy to learn more general attack features from various models. Compared to existing techniques, sufficient visualization results demonstrate that Adv-Makeup is capable to generate much more imperceptible attacks under both digital and physical scenarios. Meanwhile, extensive quantitative experiments show that Adv-Makeup can significantly improve the attack success rate under black-box setting, even attacking commercial systems.