AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability

Rohan Asthana, Vasileios Belagiannis

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 2 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 anisotropic cosine-similarity term to norm-based metric (ablation)norm of score difference metric · Detection SD v1.4 (n=1)TPR@1%FPR: 0.896 -> 0.934Improved
add anisotropic cosine-similarity term to norm-based metric (ablation)norm of score difference metric · Detection SD v2.0 (n=1)AUC: 0.948 -> 0.952Improved
add isotropic norm term to cosine-similarity metric (ablation)cosine similarity in anisotropy · Detection SD v1.4 (n=1)TPR@1%FPR: 0.424 -> 0.934Improved
use fitted gamma weights instead of equal weights (ablation)metric M · Detection SD v2.0 (n=4)TPR@1%FPR: 0.868 -> 0.900Improved
swap cosine target to conditional score vs unconditional score (ablation)metric M · Detection SD v1.4 (n=1)AUC: 0.980 vs 0.992No clear effect
use M instead of best prior denoising-free methodsharpness-based detector · Detection SD v1.4 (n=1)TPR@1%FPR: 0.908 -> 0.935Improved
use M instead of best prior denoising-free methodsharpness-based detector · Detection SD v2.0 (n=4)AUC: 0.991 -> 0.981Hurt
use M instead of best prior denoising-free methodsharpness-based detector · Detection speed SD v1.4 (n=1)time (s) per 10 prompts: 5.40 -> 1.10Improved
use M instead of best prior denoising-free methodsharpness-based detector · Detection SD v2.0 (n=1)TPR@1%FPR: 0.740 -> 0.791Improved
evaluate norm metric in anisotropic (t~0) vs isotropic (t~T) regime (ablation)Wen norm-based metric · memorized vs non-memorized separationKL divergence: 0.166 -> 0.022Hurt

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