{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:27:34Z","timestamp":1761895654533,"version":"build-2065373602"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210179","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Selective Masking Adversarial Attack on Automatic Speech Recognition Systems"],"prefix":"10.1109","author":[{"given":"Zheng","family":"Fang","sequence":"first","affiliation":[{"name":"Wuhan University,Wuhan,China"}]},{"given":"Shenyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Wuhan University,Wuhan,China"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University,Wuhan,China"}]},{"given":"Bowen","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,Wuhan,China"}]},{"given":"Lingchen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Wuhan University,Wuhan,China"}]},{"given":"Zhangyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University,Wuhan,China"}]}],"member":"263","reference":[{"year":"2023","key":"ref1","article-title":"Siri"},{"year":"2023","key":"ref2","article-title":"Whisper"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096873"},{"key":"ref6","first-page":"49","article-title":"CommanderSong: A systematic approach for practical adversarial voice recognition","volume-title":"Proc. of USENIX Security","author":"Yuan"},{"key":"ref7","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. of USENIX Security","author":"Chen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3026543"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3485383"},{"key":"ref10","first-page":"247","article-title":"KENKU: Towards efficient and stealthy black-box adversarial attacks against ASR systems","volume-title":"Proc. of USENIX Security","author":"Wu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670309"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1244"},{"key":"ref13","article-title":"Citrinet: Closing the gap between non-autoregressive and autoregressive end-to-end models for automatic speech recognition","volume":"abs\/2104.01721","author":"Majumdar","year":"2021","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1819"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsv.2016.10.043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref22","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. of ICML","author":"Radford"},{"key":"ref23","first-page":"12449","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"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"year":"2023","key":"ref26","article-title":"Nemo"},{"year":"2023","key":"ref27","article-title":"Microsoft azure speech service"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00014"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210179.pdf?arnumber=11210179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:55:10Z","timestamp":1761890110000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210179","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}