{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:18:39Z","timestamp":1774419519116,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888789","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["FreqSense: Universal and Low-Latency Adversarial Example Detection for Speaker Recognition with Interpretability in Frequency Domain"],"prefix":"10.1109","author":[{"given":"Yihuan","family":"Huang","sequence":"first","affiliation":[{"name":"Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhe","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Cyber Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhen","family":"Ren","sequence":"additional","affiliation":[{"name":"Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Tu","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Microsoft azure speaker recognition","year":"2024"},{"key":"ref2","article-title":"Amazon alexa","year":"2024"},{"key":"ref3","article-title":"Td bank voiceprint","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3485383"},{"key":"ref5","first-page":"2437","article-title":"{QFA2SR}:{Query-Free} adversarial transfer attacks to speaker recognition systems","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00009"},{"key":"ref7","first-page":"3799","article-title":"{SMACK}: Semantically meaningful adversarial audio attack","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Yu"},{"key":"ref8","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref9","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3384733"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.fa.2022-0509.202311"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414843"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2983"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053643"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3220673"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3116438"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413737"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10985"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447441"},{"key":"ref24","article-title":"Characterizing audio adversarial examples using temporal dependency","author":"Yang","year":"2018"},{"key":"ref25","first-page":"2273","article-title":"{WaveGuard}: Understanding and mitigating audio adversarial examples","volume-title":"30th USENIX security symposium (USENIX Security 21)","author":"Hussain"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746900"},{"key":"ref27","article-title":"Fraudwhistler: A resilient, robust and plug-and-play adversarial example detection method for speaker recognition","volume-title":"33th USENIX security symposium (USENIX Security 21)","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3348232"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682739"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366949"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1967.5962"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref33","article-title":"Resnet in resnet: Generalizing residual architectures","author":"Targ","year":"2016"},{"key":"ref34","article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2205"},{"key":"ref37","article-title":"Speakerguard","year":"2024"},{"key":"ref38","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888789.pdf?arnumber=10888789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:18Z","timestamp":1774416198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888789","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}