AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images

Aayush Dhakal, Subash Khanal, Srikumar Sastry, Jacob Arndt, Philipe Dias, Dalton Lunga, Nathan Jacobs

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 1 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 latent blending regularization in DINOv3 space (ablation)SimLBR (DINOv3 MLP) · Chameleon (train ProGAN)accuracy (%): 59.65 -> 84.33Improved
add latent blending regularization in DINOv3 space (ablation)SimLBR (DINOv3 MLP) · Mean accuracy over five test settingsmean accuracy (%): 78.05 -> 88.26Improved
add latent blending regularization in DINOv3 space (ablation)SimLBR (DINOv3 MLP) · Chameleon (train ProGAN), fake accuracyfake accuracy (%): 7.24 -> 75.80Improved
add latent blending regularization in DINOv3 space (ablation)SimLBR (DINOv3 MLP) · Chameleon (train SD v1.4)accuracy (%): 87.79 -> 85.57Mixed
add latent blending regularization in DINOv3 space (ablation)SimLBR (DINOv3 MLP) · GenImage (train SD v1.4)accuracy (%): 92.19 -> 94.54Improved
add latent blending regularization in DINOv3 space (ablation)SimLBR (DINOv3 MLP) · RSFakeaccuracy (%): 73.90 -> 88.88Improved
add latent blending regularization in DINOv2 space (ablation)DINOv2 MLP · Mean accuracy over test settings (DINOv2)mean accuracy (%): 68.92 -> 68.51No clear effect
use DINOv3 instead of DINOv2 features with LBR (ablation)SimLBR · Chameleon (train ProGAN)accuracy (%): 55.77 -> 84.33Improved
sample blend weight from Uniform(0.5, B) with B in 0.7-0.9 instead of only low or only high values (ablation)SimLBR · AIGC (train ProGAN)accuracyImproved
increase MLP depth beyond 4 layers (ablation)SimLBR · AIGC (train ProGAN)accuracyHurt
use SimLBR instead of AIDE on AIGC mean accuracySimLBR vs AIDE · AIGC (train ProGAN, mean over 16 test sets)mean accuracy (%): 92.77 -> 88.40Hurt
use SimLBR instead of AIDE on ChameleonSimLBR vs AIDE · Chameleon (train SD v1.4)accuracy (%): 62.60 -> 85.57Improved

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