AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

Xiao Yang, Chang Liu, Longlong Xu, Yikai Wang, Yinpeng Dong, Ning Chen, Hang Su, Jun Zhu

CVPR 2023 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 48 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
optimize adversarial meshes in 3DMM coefficient space rather than mesh spaceAT3D · CelebA-HQ, Eye & Nose, ArcFace source, API-1attack success rate (%): 75.00 -> 87.00Improved
optimize adversarial meshes in 3DMM coefficient space rather than mesh spaceAT3D · CelebA-HQ, Eye & Nose, ArcFace source, ResNet50attack success rate (%): 78.25 -> 93.75Improved
add chamfer, Laplacian, and edge-length losses to mesh-based optimization (ablation)AT3D-M · CelebA-HQ, Eye & Nose, ArcFace source, API-1attack success rate (%): 75.00 -> 75.00No clear effect
initialize shape and texture from victim coefficients and use attacker pose (ablation)AT3D-P · CelebA-HQ, Eye, ArcFace source, APIattack success rate (%): 45.25 -> 84.75Improved
optimize both shape and texture coefficients instead of shape coefficients only (ablation)AT3D-P · CelebA-HQ, Eye & Nose, ArcFace source, API-1attack success rate (%): 84.25 -> 87.00Improved
optimize both shape and texture coefficients instead of texture coefficients only (ablation)AT3D-P · CelebA-HQ, Eye & Nose, ArcFace source, API-1attack success rate (%): 77.50 -> 87.00Improved
add textured 3D meshes to the physical attackAT3D · Physical attacker-to-victim pairs, API-1mean similarity (%): 22.21 -> 82.45Improved
use AT3D meshes in physical systems with recognition and defensesAT3D · Physical attacker-to-victim pairs, S-1successful physical evaluations: 23/50Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy