AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

An Inversion-based Measure of Memorization for Diffusion Models

Zhe Ma, Qingming Li, Xuhong Zhang, Tianyu Du, Ruixiao Lin, Zonghui Wang, Shouling Ji, Wenzhi Chen

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 10 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
use adaptive weight tuning of lambda instead of fixed lambda=1 (ablation)InvMM inversion · CelebAHQ (LDM)images with infinite memorization score: 92.4% fail at lambda=1; all inverted with adaptiveImproved
use adaptive lambda instead of fixed lambda=0 (ablation)InvMM inversion · CelebAHQ, FFHQmemorization score estimateImproved
InvMM vs eps0-loss for detectionDDPM CIFAR-10 · CIFAR-10 detectionTPR@1%FPR: 0.414 -> 0.899Improved
InvMM vs Wen et al. for detectionSD v1.4 · LAION detectionAUC: 0.999 vs 0.974No clear effect
invert prompt together with noise to reveal worst-case memorizationInvMM · LAION suspicious setmemorization foundImproved
increase training epochs (ablation)LDM on CelebAHQ/FFHQ · InvMM scorememorizationHurt
increase data duplication (ablation)LDM on CelebAHQ-2.5k and FFHQ-6k · InvMM scorememorizationHurt
deduplicate training set (SD v2.1 and v3.5 vs v1.4) (ablation)Stable Diffusion · LAION confirmed and suspicious setsmemorizationImproved
increase dataset size and complexity (ablation)LDM on CelebAHQ/FFHQ · InvMM scorememorizationNo clear effect
use x0-prediction objective for inversion instead of eps0-prediction (ablation)SD v1.4 prompt inversion · confirmed setinversion stabilityImproved
use Gumbel-Softmax temperature 2.0 without discretization (ablation)SD prompt inversion · LAION subsetsdenoising errorImproved
membership inference (SecMI) vs InvMMLDM on FFHQ-6k · FFHQ-6kmembership vs memorizationMixed

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