AI Paper Atlas

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

Visual-Friendly Concept Protection via Selective Adversarial Perturbations

Xiaoyue Mi, Fan Tang, You Wu, Juan Cao, Peng Li, Yang Liu

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification

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
use VCPro instead of Anti-DreamBoothStable Diffusion v1-4 personalization protection · VGGFace2 (eps 8/255)FID (lower = less visible): 96.2 -> 27.0Improved
use VCPro instead of Anti-DreamBooth (protection strength)Textual Inversion protection · VGGFace2 (eps 8/255)LIQE (lower = stronger protection): 1.18 -> 2.31Hurt
add regional adversarial loss (RAL) to Anti-DreamBooth (ablation)Anti-DreamBooth · VGGFace2 ablationFID: 96.2 -> 68.2Improved
add Lagrangian multiplier loose solution (LMLS) to Anti-DreamBooth (ablation)Anti-DreamBooth · VGGFace2 ablationFID: 96.2 -> 30.1Improved
add LMLS to Anti-DreamBooth (ablation)Anti-DreamBooth · VGGFace2 ablation, Textual InversionCLIP-FACE: 0.05 -> 0.17Hurt
add pull term to regional adversarial loss (ablation)VCPro · VGGFace2 ablation, Textual InversionCLIP-FACE: 0.14 -> 0.03Improved
add pull term to regional adversarial loss (ablation)VCPro · VGGFace2 ablationFID: 17.2 -> 27.0Hurt
constrain perturbation with input mask instead of loss-guided mask (ablation)VCPro · VGGFace2 ablationFID: 18.6 -> 27.0Hurt
increase perturbation size from 8/255 to 16/255 (ablation)VCPro · VGGFace2FID: 27.0 -> 48.7Hurt
increase perturbation size from 8/255 to 16/255 (ablation)VCPro · VGGFace2LIQE: 2.19 -> 1.84Improved
use smaller mask with regional loss (ablation)Anti-DreamBooth+RAL · VGGFace2 ablationFID: 68.2 -> 58.4Improved

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