AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning

Renyang Liu, Guanlin Li, Tianwei Zhang, See-Kiong Ng

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 7 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 adversarially optimized image prompt to text prompt (Recall vs Text & Image) (ablation)Recall · Object-ParachuteAvg. ASR (%): 69.20 -> 97.00Improved
add adversarially optimized image prompt to text prompt (Recall vs Text & Image) (ablation)Recall · Nudity-ARTAvg. ASR (%): 5.70 -> 65.44Improved
use Recall instead of UnlearnDiffAtkunlearned SD v1.4 models · four tasksAvg. ASR (%): 16.90%, 0.20%, 11.00%, and 37.20%Improved
use latent-space multi-modal optimization instead of text-space searchRecall · Nudity attack timeattack time (s): ~64s vs ~238s (P4D-N), ~232s (UnlearnDiffAtk), ~243.15s (WACE-C)Improved
perturb only the image modality, keeping the text prompt unchangedRecall · CLIP ScoreCLIP Score: 30.28 vs 28.00 (UnlearnDiffAtk), 25.00 (P4D), 20.01 (CCE), 19.89 (WACE)Improved
use a different reference image (R1 instead of R_org) (ablation)Recall on ESD · NudityASR (%): 71.83 -> 86.62Improved
use a different reference image (R3 instead of R_org) (ablation)Recall on ESD · Object-ChurchASR (%): 96.00 -> 92.00Hurt
apply Recall to SD 2.0/2.1 instead of SD 1.4 (ablation)Recall on UCE · NudityASR (%): 76.76 -> 70.42 (SD 2.0), 68.31 (SD 2.1)No clear effect
add periodic integration of reference latent into adversarial latent (ablation)Recall · ablationASR, efficiency, diversityImproved
add noise initialization of the image prompt (ablation)Recall · ablationLPIPS, IS, CLIP ScoreImproved
reduce step size eta from 0.1 to 0.001 (ablation)Recall · ablationASR: eta 0.1 -> 0.001Improved
reduce step size eta below 0.001 (ablation)Recall · ablationASRHurt

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