AI Paper Atlas

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

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-Robust Makeup Transfer

CVPR 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 141 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use AMT-GAN instead of TIP-IMBlack-box face-recognition attacks · CelebA-HQ and LADN-dataset, four target modelsASR: CelebA-HQ IRSE50: 54.4 -> 76.96; IR152: 37.23 -> 35.13; Facenet: 40.74 -> 16.62; Mobileface: 48.72 -> 50.71. LADN IRSE50Mixed
Use AMT-GAN instead of TIP-IMAdversarial makeup images · Image quality evaluationFID: 38.7357 -> 34.4405Helped
Use AMT-GAN instead of TIP-IMAdversarial makeup images · Image quality evaluationPSNR (dB): 33.2089 -> 19.5045Hurt
Use AMT-GAN instead of TIP-IMAdversarial makeup images · Image quality evaluationSSIM: 0.9214 -> 0.7873Hurt
Add regularization module H (ablation)AMT-GAN · Image qualityFID: 37.5486 -> 34.4405Helped
Add regularization module H (ablation)AMT-GAN · Image qualityPSNR (dB): 19.3132 -> 19.5045Helped
Add regularization module H (ablation)AMT-GAN · Image qualitySSIM: 0.7807 -> 0.7873Helped

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