AI RESEARCH
Semantic-Aware Reconstruction Error for Detecting AI-Generated Images
arXiv CS.CV
•
ArXi:2508.09487v3 Announce Type: replace Recently, AI-generated image detection has gained increasing attention, as the rapid advancement of image generation technologies has raised serious concerns about their potential misuse. While existing detection methods have achieved promising results, their performance often degrades significantly when facing fake images from unseen, out-of-distribution (OOD) generative models, since they primarily rely on model-specific artifacts and thus overfit to the models used for.