AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

RA-Det: Towards Universal Detection of AI-Generated Images via Robustness Asymmetry

Xinchang Wang, Yunhao Chen, Yuechen Zhang, Congcong Bian, Zihao Guo, Xingjun Ma, Hui Li

ICML 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake 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
add discrepancy branch (ablation)RA-Det · 16 generators averageaccuracy (%): 85.73 -> 93.47Improved
add low-level residual branch (ablation)RA-Det · 16 generators averageaccuracy (%): 88.62 -> 93.47Improved
add semantic branch (ablation)RA-Det · 16 generators averageaccuracy (%): 90.34 -> 93.47Improved
use median filter instead of Gaussian filter for residual map (ablation)RA-Det residual branch · 16 generators averageaccuracy (%): 90.58 -> 93.47Improved
use learned DRP instead of Gaussian noise (ablation)RA-Det probing · 16 generators averageaccuracy (%): 86.11 -> 93.47Improved
use learned DRP instead of Gaussian blur (ablation)RA-Det probing · 16 generators averageaccuracy (%): 87.07 -> 93.47Improved
add contrastive robustness loss Lra to BCE (ablation)RA-Det · 16 generators averageaccuracy (%): 90.86 -> 93.47Improved
use DINOv3 ViT-L/16 instead of CLIP ViT-L/14 backbone (ablation)RA-Det · 16 generators averageaccuracy (%): 91.85 -> 93.47Improved
vary contrastive margin gamma 0.1 to 2.0 (ablation)RA-Det · 16 generators averageaccuracy (%): 93.47 (0.1), 90.96 (0.25), 92.67 (0.5), 93.47 (1.0), 92.31 (2.0)No clear effect
train on SDv1.4 or ProGAN+SDv1.4 instead of ProGAN onlyRA-Det · 16 generators averageaccuracy (%): 93.47 / 92.70 / 93.33No clear effect
use RA-Det learned discrepancy modeling instead of RIGID threshold scoringRA-Det vs RIGID · 16 generators averageaccuracy (%): 77.17 -> 93.47Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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