English

Robust Physical-World Attacks on Face Recognition

Computer Vision and Pattern Recognition 2021-09-21 v1

Abstract

Face recognition has been greatly facilitated by the development of deep neural networks (DNNs) and has been widely applied to many safety-critical applications. However, recent studies have shown that DNNs are very vulnerable to adversarial examples, raising serious concerns on the security of real-world face recognition. In this work, we study sticker-based physical attacks on face recognition for better understanding its adversarial robustness. To this end, we first analyze in-depth the complicated physical-world conditions confronted by attacking face recognition, including the different variations of stickers, faces, and environmental conditions. Then, we propose a novel robust physical attack framework, dubbed PadvFace, to model these challenging variations specifically. Furthermore, considering the difference in attack complexity, we propose an efficient Curriculum Adversarial Attack (CAA) algorithm that gradually adapts adversarial stickers to environmental variations from easy to complex. Finally, we construct a standardized testing protocol to facilitate the fair evaluation of physical attacks on face recognition, and extensive experiments on both dodging and impersonation attacks demonstrate the superior performance of the proposed method.

Keywords

Cite

@article{arxiv.2109.09320,
  title  = {Robust Physical-World Attacks on Face Recognition},
  author = {Xin Zheng and Yanbo Fan and Baoyuan Wu and Yong Zhang and Jue Wang and Shirui Pan},
  journal= {arXiv preprint arXiv:2109.09320},
  year   = {2021}
}

Comments

10 pages, 9 figures

R2 v1 2026-06-24T06:07:34.841Z