FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection.
arXiv:2511.06947v2 Announce Type: replace-cross Abstract: The well-aligned attribute of CLIP-based models enables its effective application like CLIPscore as a widely adopted image quality assessment metric. However, such a CLIP-based metric is vulnerable for
arXiv cs.AIResearch source·