AI Paper Atlas

Research map / Image generation / Editing and style transfer

FaceArmor: A Universal Facial Image Protection Against Diffusion-Based Manipulations

Yiming Wang, Jiahao Chen, Qingming Li, Chunyi Zhou, Zhi Chen, Lingzhong Meng, Jinbao Li, Shouling Ji

ECCV 2026 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 0 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 semantic loss LC to latent loss LE (ablation)FaceArmor · Loss ablation (mean over 4 tasks)LPIPS / FR: LPIPS 0.5215 -> 0.5329; FR 0.7615 -> 0.7540Improved
add LC, LF and LR to LE-only optimization (ablation)FaceArmor · Loss ablation (mean over 4 tasks)FR: FR 0.7615 -> 0.4522Improved
add all four losses to LE-only optimization (ablation)FaceArmor · Loss ablation (mean over 4 tasks)LPIPS: LPIPS 0.5215 -> 0.5781Improved
add region-aware (attention soft weight + PCGrad) optimization to all losses (ablation)FaceArmor · Mean over all scenariosLPIPS, SSIM, CLIP, FR (not FID)Improved
add multiple losses to LE-only baseline (ablation)FaceArmor · Mean over all scenariosFIDNo clear effect
increase perturbation budget (ablation)FaceArmor · Perturbation budget sweepprotection effectivenessImproved
increase PGD iterations from 10 to 50 (ablation)FaceArmor · Iteration sweepprotection effectivenessImproved
increase PGD iterations beyond 100 (ablation)FaceArmor · Iteration sweepprotection effectivenessNo clear effect
add EOT training with transformations (JPEG QF=75), compared with baselinesFaceArmor · Robustness, JPEG QF=75LPIPS: FaceArmor 0.557 -> 0.431 vs FaceLock 0.456 -> 0.240Improved
transfer FaceArmor perturbations (crafted on SD1.5) to SD 3FaceArmor vs AdvDM · Image Inpainting, SD3 transferLPIPS: 0.2830 -> 0.3131Improved
transfer FaceArmor perturbations to FluxFaceArmor vs AdvDM · Image Inpainting, Flux transferLPIPS: 0.2824 -> 0.2906Improved
use multi-objective multi-tier optimization instead of single-model attackFaceArmor · Computation timeseconds per image: 28.5 -> 90.2Hurt

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