When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection 事件

When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection arXiv:2605.27348v2 Announce Type: replace Abstract: Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularly in person-centric and partial-edit settings where the manipulated region is small and surrounded by photometrically authentic content. We introduce Social Gaze Consistency, a high-level semantic cue