{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:43:49Z","timestamp":1785822229612,"version":"3.56.0"},"reference-count":95,"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":"crossref","award":["62572358"],"award-info":[{"award-number":["62572358"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shandong Provincial Natural Science Foundation, China,","award":["ZR2026QC1567"],"award-info":[{"award-number":["ZR2026QC1567"]}]},{"name":"Key Research and Development Program of Shandong Province, China","award":["2025CXGC010901"],"award-info":[{"award-number":["2025CXGC010901"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2026.3714126","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:10:29Z","timestamp":1784833829000},"page":"7094-7109","source":"Crossref","is-referenced-by-count":0,"title":["UnVC: Protecting Your Voiceprint by Generative Adversarial Speech"],"prefix":"10.1109","volume":"21","author":[{"given":"Zongkun","family":"Sun","sequence":"first","affiliation":[{"name":"School of Police Information","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8939-0209","authenticated-orcid":false,"given":"Yihuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0799-5082","authenticated-orcid":false,"given":"Yanzhen","family":"Ren","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7918-6078","authenticated-orcid":false,"given":"Zixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2790-3069","authenticated-orcid":false,"given":"Wuyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Deepmind","year":"2025"},{"key":"ref2","article-title":"FoleyCrafter: Bring silent videos to life with lifelike and synchronized sounds","author":"Zhang","year":"2024","journal-title":"arXiv:2407.01494"},{"key":"ref3","volume-title":"Aphasia and Dysphasia Treatment Tools","year":"2025"},{"key":"ref4","volume-title":"Speak Screen","year":"2025"},{"key":"ref5","volume-title":"Google Assistant","year":"2025"},{"key":"ref6","volume-title":"Voice Assistant","author":"Alan","year":"2025"},{"key":"ref7","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3308474"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2298"},{"key":"ref12","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Casanova"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446863"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3530171"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0860"},{"key":"ref17","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023","journal-title":"arXiv:2303.03926"},{"key":"ref18","article-title":"Mega-TTS 2: Boosting prompting mechanisms for zero-shot speech synthesis","author":"Jiang","year":"2023","journal-title":"arXiv:2307.07218"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref20","volume-title":"Prime Voice AI.","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109507"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref24","volume-title":"Hong Kong Video Deepfake Scam"},{"key":"ref25","article-title":"How I Broke Into a Bank Account With an AI-Generated Voice","year":"2023","journal-title":"VICE"},{"key":"ref26","volume-title":"Voice Deepfakes are Coming for Your Bank Balance","author":"Time","year":"2023"},{"key":"ref27","volume-title":"AI Robocalls Mimicking Biden","author":"Time","year":"2024"},{"key":"ref28","volume-title":"AI Obama and Fake Newscasters","author":"Time","year":"2024"},{"key":"ref29","volume-title":"That\u2019s not Taylor Swift","author":"Time","year":"2024"},{"key":"ref30","volume-title":"Fretting About Election-Year Deepfakes, States Roll out New Rules for A.I","author":"Time","year":"2024"},{"key":"ref31","volume-title":"Eu Artificial Intelligence Act.","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383529"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/535"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623209"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2020.2973620"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3494962"},{"key":"ref37","first-page":"1077","article-title":"Your microphone array retains your identity: A robust voice liveness detection system for smart speakers","volume-title":"Proc. 31st USENIX Secur. Symp. (USENIX Secur.)","author":"Meng"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737422"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3163024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3367269"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TON.2025.3553313"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-023-02505-0"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746722"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-993"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980129"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446798"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1283"},{"key":"ref51","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref53","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_14"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01450"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26693"},{"key":"ref58","first-page":"7213","article-title":"UnGANable: Defending against GAN-based face manipulation","volume-title":"Proc. 32nd USENIX Secur. Symp. (USENIX Secur.)","author":"Li"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00927"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414843"},{"key":"ref61","first-page":"1","article-title":"Defense against adversarial attacks using feature scattering-based adversarial training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3184255"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3381180"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0734"},{"key":"ref65","first-page":"16199","article-title":"Robust pre-training by adversarial contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Jiang"},{"key":"ref66","first-page":"21480","article-title":"When does contrastive learning preserve adversarial robustness from pretraining to finetuning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fan"},{"key":"ref67","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen"},{"key":"ref68","article-title":"MACER: Attack-free and scalable robust training via maximizing certified radius","author":"Zhai","year":"2020","journal-title":"arXiv:2001.02378"},{"key":"ref69","first-page":"4501","article-title":"Higher-order certification for randomized smoothing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Mohapatra"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2167"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414525"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IPCCC51483.2021.9679446"},{"key":"ref73","first-page":"2273","article-title":"WaveGuard: Understanding and mitigating audio adversarial examples","volume-title":"Proc. 30th USENIX Secur. Symp. (USENIX Secur.)","author":"Hussain"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3220673"},{"key":"ref75","first-page":"2309","article-title":"Dompteur: Taming audio adversarial examples","volume-title":"Proc. 30th USENIX Secur. Symp. (USENIX Secur.)","author":"Eisenhofer"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2018.8642623"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363246"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612333"},{"key":"ref79","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref82","volume-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref83","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit, [sound]","author":"Veaux","year":"2017"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.63317\/4qazgcdhmvcm"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref86","first-page":"2437","article-title":"QFA2SR: Query-free adversarial transfer attacks to speaker recognition systems","volume-title":"Proc. 32nd USENIX Secur. Symp. (USENIX Secur.)","author":"Chen"},{"key":"ref87","article-title":"Delving into transferable adversarial examples and black-box attacks","author":"Liu","year":"2016","journal-title":"arXiv:1611.02770"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747763"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref91","article-title":"Darpa timit acoustic-phonetic continous speech corpus CD-rom","volume-title":"NIST speech disc 1-1.1","author":"Garofolo","year":"1993"},{"key":"ref92","article-title":"Better speech synthesis through scaling","author":"Betker","year":"2023","journal-title":"arXiv:2305.07243"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"issue":"1","key":"ref94","first-page":"6","article-title":"Methods for speech SNR estimation: Evaluation tool and analysis of vad dependency","volume":"14","author":"Vondrasek","year":"2005","journal-title":"Radioengineering"},{"key":"ref95","article-title":"Towards mitigating audio adversarial perturbations","volume-title":"Proc. ICLR","author":"Yang","year":"2018"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11621972.pdf?arnumber=11621972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:44:40Z","timestamp":1785818680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11621972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/tifs.2026.3714126","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}