{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T03:05:52Z","timestamp":1763348752535,"version":"3.41.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172306","62372334"],"award-info":[{"award-number":["62172306","62372334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3573182","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T17:03:38Z","timestamp":1748019818000},"page":"5152-5165","source":"Crossref","is-referenced-by-count":1,"title":["APFT: Adaptive Phoneme Filter Template to Generate Anti-Compression Speech Adversarial Example in Real-Time"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8939-0209","authenticated-orcid":false,"given":"Yihuan","family":"Huang","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0799-5082","authenticated-orcid":false,"given":"Yanzhen","family":"Ren","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6771-7215","authenticated-orcid":false,"given":"Zongkun","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3229-056X","authenticated-orcid":false,"given":"Liming","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Central China Normal University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingmin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2790-3069","authenticated-orcid":false,"given":"Wuyang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446584"},{"key":"ref2","article-title":"DistillW2 V2: A small and streaming Wav2vec 2.0 based ASR model","author":"Fu","year":"2023","journal-title":"arXiv:2303.09278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3261662"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446807"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389645"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3229526"},{"key":"ref7","article-title":"Is sora a world simulator? A comprehensive survey on general world models and beyond","author":"Zhu","year":"2024","journal-title":"arXiv:2405.03520"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3335338"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/ips.12048"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3423348"},{"key":"ref12","article-title":"Real-time neural voice camouflage","author":"Chiquier","year":"2021","journal-title":"arXiv:2112.07076"},{"key":"ref13","first-page":"5231","article-title":"Imperceptible, robust, and targeted adversarial examples for automatic speech recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qin"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1353"},{"key":"ref15","first-page":"49","article-title":"CommanderSong: A systematic approach for practical adversarial voice recognition","volume-title":"Proc. 27th USENIX Secur. Symp. (USENIX Secur.)","author":"Yuan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2022.100098"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746927"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2020.23055"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3427228.3427276"},{"key":"ref20","article-title":"Robust audio adversarial example for a physical attack","author":"Yakura","year":"2018","journal-title":"arXiv:1810.11793"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tdsc.2022.3189397"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101199"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560660"},{"key":"ref25","first-page":"513","article-title":"Hidden voice commands","volume-title":"Proc. 25th USENIX Security Symp. (USENIX Secur.)","author":"Carlini"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3384733"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3026543"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2420"},{"key":"ref29","first-page":"11908","article-title":"Adversarial music: Real world audio adversary against wake-word detection system","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref30","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3558906"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3283915"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC57359.2022.00029"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3485383"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3607199.3607240"},{"key":"ref36","first-page":"247","article-title":"KENKU: Towards efficient and stealthy black-box adversarial attacks against ASR systems","volume-title":"Proc. 32nd USENIX Secur. Symp. (USENIX Secur.)","author":"Wu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670309"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1186\/s42400-024-00218-8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23362"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3352394"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00009"},{"key":"ref42","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013","journal-title":"arXiv:1312.6199"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00014"},{"key":"ref44","first-page":"2667","article-title":"Devil\u2019s whisper: A general approach for physical adversarial attacks against commercial black-box speech recognition devices","volume-title":"Proc. 29th USENIX Secur. Symp.","author":"Chen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3359789.3359830"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737422"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3369811"},{"key":"ref50","article-title":"Characterizing audio adversarial examples using temporal dependency","author":"Yang","year":"2018","journal-title":"arXiv:1809.10875"},{"key":"ref51","first-page":"2273","article-title":"WaveGuard: Understanding and mitigating audio adversarial examples","volume-title":"Proc. 30th USENIX Secur. Symp. (USENIX Secur.)","author":"Hussain"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366949"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/89.294363"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISAP.2005.1599245"},{"volume-title":"Webrtc Api","year":"2024","key":"ref56"},{"article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","year":"2016","author":"Veaux","key":"ref57"},{"volume-title":"The Lj Speech Dataset","year":"2017","author":"Ito","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"key":"ref61","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv:1412.5567"},{"volume-title":"Google\u2019s Speech Recognition Technology Now Has a 4.9% Word Error Rate","year":"2024","key":"ref62"},{"volume-title":"Pocketsphinx 5.0.1","year":"2024","key":"ref63"},{"volume-title":"Scorer-Language Model for Determining Which Words Occur Together","year":"2024","key":"ref64"},{"volume-title":"Aukit","year":"2024","key":"ref65"},{"volume-title":"Google Assistant","year":"2024","key":"ref66"},{"volume-title":"Amazon Assistant","year":"2024","key":"ref67"},{"volume-title":"Xiaoyi","year":"2024","key":"ref68"},{"volume-title":"Xiaoai","year":"2024","key":"ref69"},{"issue":"8","key":"ref70","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"Levenshtein","year":"1966","journal-title":"Sov. Phys. Doklady"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/11014245.pdf?arnumber=11014245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T05:28:43Z","timestamp":1748582923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11014245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3573182","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"type":"print","value":"1556-6013"},{"type":"electronic","value":"1556-6021"}],"subject":[],"published":{"date-parts":[[2025]]}}}