AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstruction

Chao Wang, Zijin Yang, Yaofei Wang, Weiming Zhang, Kejiang Chen

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 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 homogeneity calibration to loss ratio (ablation)AEDR · SD2.1 targetattribution accuracy: 90.57% -> 99.66%Improved
add homogeneity calibration (ablation)AEDR · KD2.1 targetattribution accuracy: 78.35% -> 82.93%Improved
add homogeneity calibration (ablation)AEDR · FLUX targetattribution accuracy: 96.80% -> 96.65%Hurt
add homogeneity calibration (ablation)AEDR · VQDM targetattribution accuracy: 92.80% -> 90.85%Hurt
use MSE instead of LPIPS as reconstruction loss (ablation)AEDR · SD2.1 targetattribution accuracy: 90.70% -> 99.40%Improved
use MSE instead of SSIM as reconstruction loss (ablation)AEDR · SD2.1 targetattribution accuracy: 99.10% -> 99.40%No clear effect
replace single gradient-based reconstruction loss with autoencoder double-reconstruction ratioattribution method · Belonging vs other modelsattribution accuracy: 70.4% -> 95.1%Improved
replace gradient-based optimization with two autoencoder forward passesattribution method · Runtime on FLUXseconds per image: 30.64s -> 0.68sImproved
apply AEDR to quantized autoencoders instead of continuous VAEAEDR · VQ-VAE (VQDM) and MoVQ (KD2.1)attribution accuracy: 96% or more on VAE -> 90.85% (VQ-VAE), 82.93% (MoVQ)Hurt
AEDR vs LatentTracer on MoVQ modelAEDR · KD2.1 (MoVQ)attribution accuracy: 93.13% -> 82.93%Hurt

Later papers that compared with this method

1 later accepted paper reports AEDR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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