{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:01:20Z","timestamp":1764399680126,"version":"3.46.0"},"reference-count":86,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249028","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"2570-2575","source":"Crossref","is-referenced-by-count":0,"title":["Speaker Privacy and Security in the Big Data Era: Protection and Defense Against Deepfake"],"prefix":"10.1109","author":[{"given":"Liping","family":"Chen","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohan Kumar","family":"Das","sequence":"additional","affiliation":[{"name":"Fortemedia,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"School of Data Science, Chinese University of Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13943-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3530270"},{"volume-title":"CosyVoice 2: Scalable streaming speech synthesis with large language models","year":"2024","author":"Du","key":"ref5"},{"journal-title":"MegaTTS 3: Sparse alignment enhanced latent diffusion transformer for zero-shot speech synthesis","year":"2025","author":"Jiang","key":"ref6"},{"key":"ref7","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. International Conference on Machine Learning","author":"Ju","year":"2024"},{"volume-title":"General Data Protection Regulation","year":"2016","key":"ref8"},{"volume-title":"Interim Regulations for the Management of Generative Artificial Intelligence Services","key":"ref9"},{"volume-title":"Act on the Protection of Personal Information","year":"2003","key":"ref10"},{"volume-title":"Personal Data Protection Act 2012","year":"2012","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1333"},{"journal-title":"Audio deepfake detection: A survey","year":"2023","author":"Yi","key":"ref13"},{"key":"ref14","article-title":"Deep audio watermarks are shallow: Limitations of post-hoc watermarking techniques for speech","volume-title":"The 1st Workshop on GenAI Watermarking","author":"Reilly","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169066"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1983.tb04377.x"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1983.tb04378.x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1333"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2960239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1070"},{"key":"ref23","article-title":"Voicemask: Anonymize and sanitize voice input on mobile devices","volume":"abs\/1711.11460","author":"Qian","year":"2017","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274855"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3556345"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3596266"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3242292"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447699"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3689217.3690615"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3592553"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1888"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3563306"},{"journal-title":"The VoicePrivacy 2024 Challenge evaluation plan","year":"2024","author":"Tomashenko","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190741"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3519879"},{"volume-title":"Overview of the voiceprivacy 2024 challenge","year":"2024","author":"Tomashenko","key":"ref36"},{"key":"ref37","article-title":"Explaining and harnessing adversarial examples","volume-title":"International Conference on Learning Representations","author":"Goodfellow","year":"2014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-022-00782-x"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3714458"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"journal-title":"Beware the Artificial Impostor: A McAfee Cybersecurity Artificial Intelligence Report","year":"2023","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.21"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-472"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414234"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-14"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2892"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3547861"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-1"},{"journal-title":"ADD 2023: The second audio deepfake detection challenge","year":"2023","author":"Yi","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650962"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2428"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2025.3529377"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3569430"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"volume-title":"Speech arena: Speech deepfake leaderboard","year":"2025","author":"Arena","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2025.101840"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755851"},{"key":"ref65","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383572"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1283"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-31"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1996.560429"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24200"},{"journal-title":"Wavmark: Watermarking for audio generation","year":"2023","author":"Chen","key":"ref71"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2016.04.005"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/5.771068"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-45619-w"},{"journal-title":"SoK: How robust is audio watermarking in generative AI models?","year":"2025","author":"Wen","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447253"},{"key":"ref77","article-title":"Proactive detection of voice cloning with localized watermarking","volume-title":"Proc. ICML","author":"Roman","year":"2024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/app14166897"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448134"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888976"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3456673"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-534"},{"key":"ref83","first-page":"52 241","article-title":"Audiomarkbench: Benchmarking robustness of audio watermarking","volume":"37","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1530"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2005.855418"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865703304081"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249028.pdf?arnumber=11249028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:57:21Z","timestamp":1764399441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249028\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249028","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}