{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:09:11Z","timestamp":1781586551625,"version":"3.54.5"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022646","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"692-699","source":"Crossref","is-referenced-by-count":4,"title":["Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection"],"prefix":"10.1109","author":[{"given":"Xuanjun","family":"Chen","sequence":"first","affiliation":[{"name":"National Taiwan University,Department. of Computer Science Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibin","family":"Wu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Centre for Perceptual and Interactive Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyh-Shing Roger","family":"Jang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department. of Computer Science Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref3","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413737"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1452"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-020-01629-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053747"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2430"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133189"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1052"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746900"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3376897.3377856"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1343"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413467"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11142183"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/asru46091.2019.9003763"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102988"},{"key":"ref22","article-title":"Practical attacks on voice spoofing countermeasures","author":"Kassis","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053643"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/741"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00016"},{"key":"ref27","first-page":"5231","article-title":"Imperceptible, robust, and targeted adver-sarial examples for automatic speech recognition","volume-title":"Inter-national conference on machine learning","author":"Qin"},{"key":"ref28","article-title":"Did you hear that? adversarial examples against automatic speech recognition","author":"Alzantot","year":"2018","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23288"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053288"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746124"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2800728"},{"key":"ref34","first-page":"87","article-title":"Whos speaking? audio-supervised classi-fication of active speakers in video","volume-title":"Proceedings of the 2015 ACM on International Conference on Multimodal Interaction","author":"Chakravarty"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00238"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2463722"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00123"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-80"},{"key":"ref42","article-title":"Sub-word level lip reading with visual attention","author":"Afouras","year":"2021","journal-title":"ar Xiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref44","article-title":"N aver at activitynet challenge 2019-task b active speaker detection (ava)","author":"Chung","year":"2019","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00033"},{"key":"ref47","first-page":"1","article-title":"Multi-task learning for audio-visual active speaker detection","author":"Zhang","year":"2019","journal-title":"The ActivityNet Large-Scale Activity Recognition Challenge"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1017\/9781108552332"},{"key":"ref50","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"ar Xiv preprint"},{"key":"ref51","article-title":"Adversarial examples in the physical world. arxiv 2016","author":"Kurakin","year":"2016","journal-title":"ar Xiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00957"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref54","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv preprint"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022646.pdf?arnumber=10022646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:39:30Z","timestamp":1707813570000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022646\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022646","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}