From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection 事件

From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection arXiv:2605.27944v1 Announce Type: new Abstract: With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection typically rely on cross-modal inconsistencies. In singing, rhythmic vocalization weakens this coupling and introduces a nontrivial domain shift, substantially degrading detection performance. We construct the