AI Paper Atlas

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

Towards Face Encryption by Generating Adversarial Identity Masks

Xiao Yang, Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu, Yuefeng Chen, Hui Xue

ICCV 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 129 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 multi-target optimization (MT-DIM over single-target DIM)DIM · LFW black-box, ArcFace surrogate to MobileFaceRank-1-T: 16.8 -> 18.8Improved
replace Center-Opt gain with greedy insertion (TIP-IM) (ablation)Center-Opt · LFW black-box, ArcFace surrogate to MobileFaceRank-1-T: 36.8 -> 69.8Improved
replace Center-Opt gain with greedy insertion (TIP-IM) (ablation)Center-Opt · LFW black-box, ArcFace surrogate to ResNet50Rank-1-T: 28.8 -> 56.0Improved
replace Center-Opt gain with greedy insertion (TIP-IM) (ablation)Center-Opt · LFW black-box, ArcFace surrogate to CosFaceRank-1-T: 3.8 -> 11.4Improved
TIP-IM over best prior baseline MT-DIMMT-DIM · LFW black-box, ArcFace surrogate to FaceNetRank-1-T: 9.6 -> 32.8Improved
increase MMD weight gamma from 0.0 to 3.0 (ablation)TIP-IM (ArcFace) · LFW naturalnessPSNR (dB): 25.26 -> 27.63Improved
increase MMD weight gamma from 0.0 to 3.0 (ablation)TIP-IM (ArcFace) · LFW naturalnessSSIM: 0.6520 -> 0.7817Improved
increase MMD weight gamma from 0.0 to 3.0 (ablation)TIP-IM (ArcFace) · LFW naturalnessMMD (lower better): 0.7567 -> 0.7518Improved
increase gamma (stronger naturalness) (ablation)TIP-IM · LFW targeted protectionRank-1-THurt
increase MMD batch size from 10 to 50 (ablation)TIP-IM (CosFace) · LFW naturalnessSSIM: 0.8518 -> 0.6759Hurt
increase number of target identities (ablation)TIP-IM (MobileFace surrogate) · black-box identity protectionRank-1-TImproved
use StyleGAN generated faces as targets instead of real identities (ablation)TIP-IM · MegFace/LFW black-boxRank-1-T: 49.6No clear effect

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