AI RESEARCH

Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detection

arXiv CS.CV

ArXi:2605.07074v1 Announce Type: new Detecting AI-generated images across unseen architectures remains challenging, as existing models often overfit to generator-specific fingerprints and semantic content rather than learning universal forgery traces. We attribute this failure to feature entanglement: detectors learn these factors as a single entangled representation, where universal forgery traces are inextricably confounded with both generator-specific fingerprints and semantic content.