MuDD: A Multimodal Deception Detection Dataset and GSR-Guided Progressive Distillation for Non-Contact Deception Detection

ArXi:2603.26064v1 Announce Type: cross Non-contact automatic deception detection remains challenging because visual and auditory deception cues often lack stable cross-subject patterns. In contrast, galvanic skin response (GSR) provides reliable physiological cues and has been widely used in contact-based deception detection. In this work, we leverage stable deception-related knowledge in GSR to guide representation learning in non-contact modalities through cross-modal knowledge distillation. A key obstacle, however, is the lack of a suitable dataset for this setting. To address this, we