{"ID":2847615,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.27475","arxiv_id":"2510.27475","title":"Referee: Reference-aware Audiovisual Deepfake Detection","abstract":"Deepfakes generated by advanced generative models have rapidly posed serious threats, yet existing audiovisual deepfake detection approaches struggle to generalize to unseen manipulation methods. To address this, we propose a novel reference-aware audiovisual deepfake detection method, called Referee to capture fine-grained identity discrepancies. Unlike existing methods that overfit to transient spatiotemporal artifacts, Referee employs identity bottleneck and matching modules to model the relational consistency of speaker-specific cues captured by a single one-shot example as a biometric anchor. Extensive experiments on FakeAVCeleb, FaceForensics++, and KoDF demonstrate that Referee achieves state-of-the-art results on cross-dataset and cross-language evaluation protocols, including a 99.4% AUC on KoDF. These results highlight that explicitly correlating reference-based biometric priors is a key frontier for achieving generalized and reliable audiovisual forensics. The code is available at https://github.com/ewha-mmai/referee.","short_abstract":"Deepfakes generated by advanced generative models have rapidly posed serious threats, yet existing audiovisual deepfake detection approaches struggle to generalize to unseen manipulation methods. To address this, we propose a novel reference-aware audiovisual deepfake detection method, called Referee to capture fine-gr...","url_abs":"https://arxiv.org/abs/2510.27475","url_pdf":"https://arxiv.org/pdf/2510.27475v2","authors":"[\"Hyemin Boo\",\"Eunsang Lee\",\"Jiyoung Lee\"]","published":"2025-10-31T13:54:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.MM\"]","methods":"[]","has_code":false,"code_links":[{"ID":607545,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2847615,"paper_url":"https://arxiv.org/abs/2510.27475","paper_title":"Referee: Reference-aware Audiovisual Deepfake Detection","repo_url":"https://github.com/ewha-mmai/referee","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}