Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition
Lists
Only you see this
Abstract
Face recognition is a prevailing authentication solution in numerous biometric applications. Physical adversarial attacks, as an important surrogate, can identify the weak-nesses of face recognition systems and evaluate their ro-bustness before deployed. However, most existing physical attacks are either detectable readily or ineffective against commercial recognition systems. The goal of this work is to develop a more reliable technique that can carry out an end-to-end evaluation of adversarial robustness for commercial systems. It requires that this technique can simultaneously deceive black-box recognition models and evade defensive mechanisms. To fulfill this, we design adversarial textured 3D meshes (AT3D) with an elaborate topology on a human face, which can be 3D-printed and pasted on the attacker's face to evade the defenses. However, the mesh-based op-timization regime calculates gradients in high-dimensional mesh space, and can be trapped into local optima with un-satisfactory transferability. To deviate from the mesh-based space, we propose to perturb the low-dimensional coefficient space based on 3D Morphable Model, which signifi-cantly improves black-box transferability meanwhile enjoying faster search efficiency and better visual quality. Exten-sive experiments in digital and physical scenarios show that our method effectively explores the security vulnerabilities of multiple popular commercial services, including three recognition A PIs, four anti-spoofing A PIs, two prevailing mobile phones and two automated access control systems.
BibTeX
@inproceedings{yang2023towards,
author = {Xiao Yang and Chang Liu and Longlong Xu and Yikai Wang and Yinpeng Dong and Ning Chen and Hang Su and Jun Zhu},
title = {{Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition}},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2023},
doi = {10.1109/cvpr52729.2023.00401},
}