AI RESEARCH
DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization
arXiv CS.CV
•
ArXi:2604.12443v1 Announce Type: new Modern diffusion-based inpainting models pose significant challenges for image forgery localization (IFL), as their full regeneration pipelines reconstruct the entire image via a latent decoder, disrupting the camera-level noise patterns that existing forensic methods rely on. We propose DiffusionPrint, a patch-level contrastive learning framework that learns a forensic signal robust to the spectral distortions