Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition

Yin, Bangjie; Wang, Wenxuan; Yao, Taiping; Guo, Junfeng; Kong, Zelun; Ding, Shouhong; Li, Jilin; Liu, Cong

doi:10.24963/ijcai.2021/173

Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition

Bangjie Yin, Wenxuan Wang, Taiping Yao, Junfeng Guo, Zelun Kong, Shouhong Ding, Jilin Li, Cong Liu

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1252-1258.

https://doi.org/10.24963/ijcai.2021/173

Keywords

Computer Vision: Biometrics, Face and Gesture Recognition
Machine Learning: Adversarial Machine Learning
Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation

Abstract

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 the 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 based adversarial attack strategy to learn more vulnerable or sensitive 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.

Bangjie Yin, Wenxuan Wang, Taiping Yao, Junfeng Guo, Zelun Kong, Shouhong Ding, Jilin Li, and Cong Liu. 2021. Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 1252–1258. https://doi.org/10.24963/ijcai.2021/173

@inproceedings{ijcai2021p173,
  title     = {Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition},
  author    = {Yin, Bangjie and Wang, Wenxuan and Yao, Taiping and Guo, Junfeng and Kong, Zelun and Ding, Shouhong and Li, Jilin and Liu, Cong},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {1252--1258},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/173},
  url       = {https://doi.org/10.24963/ijcai.2021/173},
}

TY  - CPAPER
TI  - Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition
AU  - Yin, Bangjie
AU  - Wang, Wenxuan
AU  - Yao, Taiping
AU  - Guo, Junfeng
AU  - Kong, Zelun
AU  - Ding, Shouhong
AU  - Li, Jilin
AU  - Liu, Cong
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 1252
EP  - 1258
DO  - 10.24963/ijcai.2021/173
UR  - https://doi.org/10.24963/ijcai.2021/173
ER  -