AI Paper Atlas

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

Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification

Wenkui Yang, Jie Cao, Junxian Duan, Ran He

ICCV 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 3 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 patch-wise frequency guidance to the DDPM loss (ablation)AntiPure · VGGFace2 (DreamBooth after purification)ISM: 0.5958 -> 0.5644Improved
add patch-wise frequency guidance to the DDPM loss (ablation)AntiPure · CelebA-HQ (DreamBooth after purification)ISM: 0.6293 -> 0.6253No clear effect
add erroneous timestep guidance to the DDPM loss (ablation)AntiPure · VGGFace2 (DreamBooth after purification)ISM: 0.5958 -> 0.5901Improved
add erroneous timestep guidance to the DDPM loss (ablation)AntiPure · CelebA-HQ (DreamBooth after purification)ISM: 0.6293 -> 0.6489Hurt
use both guidances together (full AntiPure) over DDPM loss alone (ablation)AntiPure · CelebA-HQ (DreamBooth after purification)FID: 69.06 -> 81.15Improved
use both guidances together (full AntiPure) over DDPM loss alone (ablation)AntiPure · VGGFace2 (DreamBooth after purification)FID: 76.32 -> 90.77Improved
more purification iterations (10 to 40) against AntiPure (ablation)AntiPure · CelebA-HQ (DreamBooth, purification iterations)ISM: 0.6362 -> 0.5994Improved
more purification iterations (10 to 40) against Anti-DB (ablation)Anti-DB · CelebA-HQ (DreamBooth, purification iterations)ISM: 0.6020 -> 0.6391Hurt
replace Anti-DB with AntiPure after purificationDreamBooth P-C workflow · CelebA-HQ (DreamBooth after purification)ISM: 0.6422 -> 0.6112Improved
swap DreamBooth for LoRA fine-tuning with AntiPureAntiPure vs Anti-DB · VGGFace2 (LoRA after purification)ISM: 0.5723 -> 0.5428Improved
lambda1/lambda2 0.25/0.75 instead of 0.5/0.5 (ablation)AntiPure · VGGFace2 (DreamBooth after purification)ISM: 0.5475 -> 0.5431No clear effect
lambda1/lambda2 0.75/0.25 instead of 0.5/0.5 (ablation)AntiPure · VGGFace2 (DreamBooth after purification)ISM: 0.5475 -> 0.5586No 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