AI Paper Atlas

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

Privacy-Preserving Adversarial Facial Features

Zhibo Wang, He Wang, Shuaifan Jin, Wenwen Zhang, Jiahui Hu, Yan Wang, Peng Sun, Wei Yuan, Kaixin Liu, Kui Ren

CVPR 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Neural network watermarking · 39 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
Replace unprotected features with AdvFace adversarial featuresFace recognition features · LFWSRRA: 97.40% -> 4.03%Improved
Replace unprotected features with AdvFace adversarial featuresFace recognition features · CFP-FPSRRA: 89.71% -> 18.43%Improved
Replace unprotected features with AdvFace adversarial featuresFace recognition features · AgeDB-30SRRA: 84.53% -> 16.67%Improved
Add bounded adversarial latent noise through AdvFaceFace recognition features · LFWaccuracy: 98.13% -> 96.43%Hurt
Add bounded adversarial latent noise through AdvFaceFace recognition features · CFP-FPaccuracy: 93.16% -> 90.59%Hurt
Add bounded adversarial latent noise through AdvFaceFace recognition features · AgeDB-30accuracy: 87.57% -> 85.10%Hurt
Retrain the server-side recognition network using adversarial featuresAdvFace · LFWaccuracy: 96.43% -> 97.78%Improved
Retrain the server-side recognition network using adversarial featuresAdvFace · CFP-FPaccuracy: 90.59% -> 92.04%Improved
Retrain the server-side recognition network using adversarial featuresAdvFace · AgeDB-30accuracy: 85.10% -> 86.35%Improved
Use TransRec rather than ResRec as the shadow model (ablation)AdvFace · LFW, CFP-FP, AgeDB-30accuracy: 96.43% -> 96.53%; 90.59% -> 90.77%; 85.10% -> 85.13%No clear effect
Use URec rather than ResRec as the shadow model (ablation)AdvFace · LFW, CFP-FP, AgeDB-30accuracy: 96.43% -> 96.42%; 90.59% -> 90.13%; 85.10% -> 84.58%Hurt

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