AI RESEARCH
HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
arXiv CS.LG
•
ArXi:2412.20704v2 Announce Type: replace-cross Dramatic advances in the quality of the latent diffusion models (LDMs) also led to the malicious use of AI-generated images. While current AI-generated image detection methods assume the availability of real/AI-generated images for