AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders

Syed Irfan Ali Meerza, Oktay Ozturk, Amir Sadovnik, Jian Liu

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Reconstruction-based diffusion image detection · 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
inject noise in semantic space instead of pixel space (vs SEM)DiffUE · CIFAR-10, adversarial training rho_t=4/255test accuracy (lower is better): 46.85 -> 17.11Improved
semantic noise vs pixel noise under adversarial trainingDiffUE · ImageNet Subset, rho_t=4/255test accuracy (lower is better): 38.57 -> 17.20Improved
semantic noise under mean filteringDiffUE · CIFAR-10test accuracy (lower is better): 28.55 -> 13.32Improved
semantic noise against UEraserDiffUE · CIFAR-10test accuracy (lower is better): 81.56 -> 14.19Improved
semantic noise against LUE diffusion purificationDiffUE · CIFAR-10test accuracy (lower is better): 89.29 -> 33.97Improved
semantic noise under JPEG compressionDiffUE · CIFAR-10test accuracy (lower is better): 45.22 -> 17.22Improved
semantic noise vs pixel noise without any defenseDiffUE · ImageNet, no compression/attacktest accuracy (lower is better): 1.89 -> 2.11No clear effect
semantic noise transferred from ResNet-18 to VGG-16DiffUE · CIFAR-10test accuracy (lower is better): 54.55 -> 25.33Improved
semantic noise improves perceptual quality (FID)DiffUE · CelebA-HQFID: 10.145 -> 5.355Improved
semantic noise improves image naturalness in user studyDiffUE · User studynaturalness: 3.11 -> 4.65Improved
larger semantic noise radius for stronger unlearnabilityDiffUE · semantic radius selectionunlearnability vs semanticsMixed

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