AI RESEARCH
Rethinking VLMs for Image Forgery Detection and Localization
arXiv CS.LG
•
ArXi:2603.12930v1 Announce Type: cross With the rapid rise of Artificial Intelligence Generated Content (AIGC), image manipulation has become increasingly accessible, posing significant challenges for image forgery detection and localization (IFDL). In this paper, we study how to fully leverage vision-language models (VLMs) to assist the IFDL task. In particular, we observe that priors from VLMs hardly benefit the detection and localization performance and even have negative effects due to their inherent biases toward semantic plausibility rather than authenticity.