Yinpeng Dong, Hang Su, Jun Zhu, Xiao Yang, Chang Liu, Yikai Wang, Ning Chen, Longlong Xu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Face recognition is a prevailing authentication solution in numerous biometric applications. Physical adversarial attacks, as an important surrogate, can identify the weaknesses of face recognition systems and evaluate their robustness 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 endto-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 optimization regime calculates gradients in high-dimensional mesh space, and can be trapped into local optima with unsatisfactory transferability. To deviate from the mesh-based space, we propose to perturb the low-dimensional coefficient space based on 3D Morphable Model, which significantly improves black-box transferability meanwhile enjoying faster search efficiency and better visual quality. Extensive experiments in digital and physical scenarios show that our method effectively explores the security vulnerabilities of multiple popular commercial services, including three recognition APIs, four anti-spoofing APIs, two prevailing mobile phones and two automated access control systems. This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore. Frames [28] AdvHat [17] FaceAdv [29] PadvFace [50] AdvMask [52] Face3DAdv [40] RHDE [35] Ours 3D attack types No Partially Partially No Yes Yes Partially Yes Commercial recognition Yes No No No No No Yes Yes Commercial defenses No No No No No Yes No Yes Number of physical tests 10 3 10 10 30 10 3 50 Table 1. A comparison among different methods regarding whether using 3D attack types, commercial face recognition models, commercial defenses, and the number of physical evaluation. Partially indicates that this method involved some geometric transformations to make 2D patch approximately approach the realistic 3D patch.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.15818")
get_code_for_paper("2303.15818")
have("2303.15818")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.15818.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.15818)
Connect an agent — have() is free.