AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

3D-Aware Adversarial Makeup Generation for Facial Privacy Protection

Yueming Lyu, Yue Jiang, Ziwen He, Bo Peng, Yunfan Liu, Jing Dong

TPAMI 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 19 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
add Makeup Adjustment Module (MAM) (ablation)3DAM-GAN · Makeup generation qualityFID: 31.52 -> 26.78Improved
add Makeup Adjustment Module (MAM) (ablation)3DAM-GAN · Makeup generation qualityPSNR: 19.63 -> 20.82Improved
add Makeup Adjustment Module (MAM) (ablation)3DAM-GAN · Makeup generation qualitySSIM: 0.90 -> 0.91Improved
add UV makeup loss (ablation)3DAM-GAN · Makeup generation qualityFID: 35.63 -> 26.78Improved
add UV makeup loss (ablation)3DAM-GAN · Makeup generation qualityPSNR: 19.29 -> 20.82Improved
add UV makeup loss (ablation)3DAM-GAN · Makeup generation qualitySSIM: 0.89 -> 0.91Improved
UV-space 3D-aware makeup generation instead of 2D makeup transfer (vs AMT-GAN)3DAM-GAN · CelebA-HQ black-box, FaceNet targetASR at 0.01 FAR (%): 47.10 -> 64.33Improved
UV-space makeup generation vs AMT-GAN3DAM-GAN · CelebA-HQ black-box, IR152 targetASR at 0.01 FAR (%): 36.27 -> 57.04Improved
UV-space makeup generation vs AMT-GAN3DAM-GAN · LADN black-box, MobileFace targetASR at 0.01 FAR (%): 88.98 -> 88.65Hurt
UV-space makeup generation vs AMT-GAN3DAM-GAN · LFW face verification, FaceNetPSR at 0.01 FAR (%): 26.68 -> 82.78Improved
UV-space makeup generation vs AMT-GAN3DAM-GAN · CelebA-HQ face identification, IRSE50Rank-1 protection success rate (%): 71.81 -> 95.52Improved
full-face UV makeup instead of eye-shadow patch (vs Adv-Makeup) in image quality3DAM-GAN · Makeup generation qualityFID: 3.05 -> 26.78Hurt

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