SOURCE-LINKED INTELLIGENCE

FUSED: Forensic-Semantic Mixture-of-Experts for AI Inpainting Detection and Localization

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Diffusion-based inpainting models modify only a localized part of an image, while many AI-image detectors rely on global artifacts and do not localize. These artifacts vary across generators, limiting detector transfer under distribution shifts. Recent work shows that restoring the authentic pixels outside the inpainted region removes these cues and can degrade pretrained detectors. To address this, we present FUSED, a unified framework for the joint detection and localization of AI-generated inpainting. FUSED combines low-level forensic cues with high-level semantic features using a sparsely-

Read original source ↗ Open in workspace

recordType

paper

region

Global