{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T07:34:19Z","timestamp":1774078459154,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2022"],"award-info":[{"award-number":["U23B2022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2030"],"award-info":[{"award-number":["U22A2030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Major Project of Basic and Applied Basic Research","award":["2023B0303000010"],"award-info":[{"award-number":["2023B0303000010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2026.3673104","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:35:05Z","timestamp":1773347705000},"page":"2933-2946","source":"Crossref","is-referenced-by-count":0,"title":["Toward Generalizable Deepfake Detection via Forgery-Aware Audio\u2013Visual Adaptation: A Variational Bayesian Approach"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6867-498X","authenticated-orcid":false,"given":"Fan","family":"Nie","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7520-9031","authenticated-orcid":false,"given":"Jiangqun","family":"Ni","sequence":"additional","affiliation":[{"name":"Department of New Networks, Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9632-3785","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"}]},{"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of New Networks, Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4783-876X","authenticated-orcid":false,"given":"Weizhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of New Networks, Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2613-5451","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Guangdong Key Laboratory of Intelligent Information Processing, and Shenzhen Key Laboratory of Media Security, Shenzhen University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02367"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309899"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312738"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref16","first-page":"6100","article-title":"Multimodal generative learning utilizing Jensen\u2013Shannon\u2013Divergence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutter"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681672"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref22","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv:1809.00496"},{"key":"ref23","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref24","first-page":"26462","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2445"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00190"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02536"},{"key":"ref29","article-title":"DeepFake-adapter: Dual-level adapter for DeepFake detection","author":"Shao","year":"2023","journal-title":"arXiv:2306.00863"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3522091"},{"key":"ref31","article-title":"MoE-FFD: Mixture of experts for generalized and parameter-efficient face forgery detection","author":"Kong","year":"2024","journal-title":"arXiv:2404.08452"},{"key":"ref32","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref33","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sohn"},{"key":"ref34","first-page":"15692","article-title":"Variational mixture-of-experts autoencoders for multi-modal deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Shi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313552"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105515"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.01.001"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2359098"},{"key":"ref39","first-page":"102","article-title":"BIRD: Learning binary and illumination robust descriptor for face recognition","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Su"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01963"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref42","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Khalid"},{"key":"ref43","volume-title":"FaceSwap","author":"Marek","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"ref45","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01057"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109628"},{"key":"ref48","first-page":"7135","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Siarohin"},{"key":"ref49","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020","journal-title":"arXiv:2002.10137"},{"key":"ref50","article-title":"The VidTIMIT database","author":"Sanderson","year":"2002"},{"key":"ref51","article-title":"The DeepFake detection challenge (DFDC) dataset","author":"Dolhansky","year":"2020","journal-title":"arXiv:2006.07397"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1416"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103818"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680622"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00170"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref59","first-page":"13826","article-title":"Intra-modal and cross-modal synchronization for audio-visual deepfake detection and temporal localization","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Anshul"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11430622.pdf?arnumber=11430622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T04:39:04Z","timestamp":1774067944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11430622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tifs.2026.3673104","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}