AI Paper Atlas

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

Anti-Tamper Protection for Unauthorized Individual Image Generation

Zelin Li, Ruohan Zong, Yifan Liu, Ruichen Yao, Yaokun Liu, Yang Zhang, Dong Wang

ICCV 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 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 ATP to MetaCloakMetaCloak · CelebA-HQ (no purification)FDFR: 0.4850 -> 0.7038Improved
add ATP to Anti-DBAnti-DB · VGGFace2 (no purification)FDFR: 0.6788 -> 0.8188Improved
add ATP to CAATCAAT · VGGFace2 (no purification)FDFR: 0.7825 -> 0.7863No clear effect
add ATP to MetaCloakMetaCloak · CelebA-HQ (no purification)ISM: 0.4911 -> 0.4048Improved
add mask guidance in pixel domain (ablation)Anti-DB+ATP · CelebA-HQ bit-errorBit-error (x1e-3): 349.84 -> 42.031Improved
add BDCT frequency domain with mask and Improved-PGD (ablation)Anti-DB+ATP · CelebA-HQ bit-errorBit-error (x1e-3): 42.031 -> 0.4688Improved
add Improved-PGD algorithm to BDCT+mask (ablation)Anti-DB+ATP · CelebA-HQ bit-errorBit-error (x1e-3): 81.719 -> 0.4688Improved
add BDCT without mask (ablation)Anti-DB+ATP · CelebA-HQ bit-errorBit-error (x1e-3): 349.84 -> 360.31Hurt
raise mask ratio from 0.5 to 0.75 (ablation)ATP · CelebA-HQBit-error (x1e-3): 0.4688 -> 0.3125Mixed
lower mask ratio from 0.5 to 0.25 (ablation)ATP · CelebA-HQFDFR: 0.5213 -> 0.6400Mixed
add protection perturbation to authorization perturbation (ablation)Authorization alone · CelebA-HQFDFR: 0.1075 -> 0.6338Improved
add ATP tamper-proof mechanism under purificationMetaCloak · CelebA-HQ and VGGFace2 (purification)PSRImproved

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