{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T20:20:27Z","timestamp":1778617227042,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":"publisher","award":["U2336206"],"award-info":[{"award-number":["U2336206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402469"],"award-info":[{"award-number":["62402469"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62121002"],"award-info":[{"award-number":["62121002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472398"],"award-info":[{"award-number":["62472398"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI Singapore Programme AISG","award":["AISG3-RPGV-2025-019"],"award-info":[{"award-number":["AISG3-RPGV-2025-019"]}]},{"name":"AoE from the RGC of Hong Kong","award":["AoE\/E-601\/24-N"],"award-info":[{"award-number":["AoE\/E-601\/24-N"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3658817","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:59:22Z","timestamp":1769633962000},"page":"6509-6524","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Security Vulnerabilities in Multilingual Speech Translation Systems via Deceptive Inputs"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3997-5264","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0493-5013","authenticated-orcid":false,"given":"Haolin","family":"Wu","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Yang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Noah&#x2019;s Ark Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0930-0283","authenticated-orcid":false,"given":"Cong","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5576-6108","authenticated-orcid":false,"given":"Weiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-9316","authenticated-orcid":false,"given":"Nenghai","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-6650","authenticated-orcid":false,"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0974-9299","authenticated-orcid":false,"given":"Qing","family":"Guo","sequence":"additional","affiliation":[{"name":"CFAR and IHPC, A&#x002A;STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4230-1077","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"CFAR and IHPC, A&#x002A;STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7753\/IJCATR1103.1001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3202047"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599557"},{"key":"ref4","volume-title":"Verbmobil: Foundations of Speech-to-Speech Translation","author":"Wahlster","year":"2013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860774"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref7","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445811"},{"key":"ref9","article-title":"Canary"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-726"},{"key":"ref12","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","author":"B\u00b4erard","year":"2016","journal-title":"NIPS Workshop End-To-End Learn. Speech Audio Process."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1326"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054626"},{"key":"ref15","article-title":"SeamlessM4T-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383529"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623209"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3627106.3627183"},{"key":"ref19","first-page":"3799","article-title":"Smack: Semantically meaningful adversarial audio attack","volume-title":"Proc. 32nd USENIX Secur.","author":"Yu","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/sp54263.2024.00056"},{"key":"ref21","first-page":"49","article-title":"CommanderSong: A systematic approach for practical adversarial voice recognition","volume-title":"Proc. 27th USENIX Secur. Symp.","author":"Yuan","year":"2018"},{"key":"ref22","first-page":"513","article-title":"Hidden voice commands","volume-title":"Proc. 25th USENIX Secur. Symp.","author":"Carlini","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/741"},{"key":"ref24","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","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3559350"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560671"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3328253"},{"key":"ref29","first-page":"2437","article-title":"QFA2SR:query-free adversarial transfer attacks to speaker recognition systems","volume-title":"Proc. 32nd USENIX Secur. Symp.","author":"Chen","year":"2023"},{"key":"ref30","article-title":"Seamless communication","author":"AI","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref33","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447368"},{"key":"ref35","article-title":"Transfool: An adversarial attack against neural machine translation models","author":"Sadrizadeh","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.153"},{"key":"ref37","first-page":"653","article-title":"On adversarial examples for character-level neural machine translation","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Ebrahimi"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450034"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095342"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.126"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3376897.3377856"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053747"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447190"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3597552"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00041"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00382"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref51","first-page":"450","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. PMLR","author":"Liu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.459"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"key":"ref56","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Yamagishi","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref58","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. Twelfth Lang. Resour. Eval. Conf.","author":"Ardila"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24200"},{"key":"ref63","article-title":"Resemblyzer","author":"Jemine","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"ref66","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11367280.pdf?arnumber=11367280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:48:48Z","timestamp":1778615328000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11367280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":67,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3658817","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}