{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:30:24Z","timestamp":1776882624214,"version":"3.51.2"},"reference-count":33,"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\/icassp49660.2025.10890611","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models"],"prefix":"10.1109","author":[{"given":"Nikolai L.","family":"K\u00fchne","sequence":"first","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Astrid H. F.","family":"Kitchena","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie S.","family":"Jensen","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikkel S. L.","family":"Br\u00f8ndt","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Gonzalez","sequence":"additional","affiliation":[{"name":"IRT SystemX,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christophe","family":"Biscio","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Intriguing properties of neural networks","volume-title":"2nd International Conference on Learning Representations","author":"Szegedy"},{"key":"ref2","article-title":"Explaining and harnessing adversarial examples","volume-title":"International Conference on Learning Representations","author":"Goodfellow"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref4","article-title":"Houdini: Fooling deep structured visual and speech recognition models with adversarial examples","volume":"30","author":"Cisse","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"49","article-title":"{CommanderSong}: a systematic approach for practical adversarial voice recognition","volume-title":"27th USENIX security symposium (USENIX security 18)","author":"Yuan"},{"key":"ref6","first-page":"5231","article-title":"Imperceptible, robust, and targeted adversarial examples for automatic speech recognition","volume-title":"International conference on machine learning","author":"Qin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3384733"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00429"},{"key":"ref12","article-title":"Characterizing audio adversarial examples using temporal dependency","volume-title":"International Conference on Learning Representations","author":"Yang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/isspit.2018.8642623"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3220673"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref18","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"Proceedings of the International Conference on Representation Learning","author":"Madry"},{"key":"ref19","article-title":"Defending against adversarial audio via diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wu"},{"key":"ref20","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref23","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2021","journal-title":"ICLR 2021 (oral)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054750"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2023.3256321"},{"key":"ref26","first-page":"2273","article-title":"WaveGuard: Understanding and mitigating audio adversarial examples","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Hussain"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.103061"},{"key":"ref28","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)","author":"Ardila"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref30","article-title":"Auto-encoding variational bayes","volume-title":"International Conference on Learning Representations","author":"Kingma"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.csl.2019.06.005","article-title":"rVAD: An unsupervised segment-based robust voice activity detection method","volume":"59","author":"Tan","year":"2020","journal-title":"Computer speech & language"},{"key":"ref33","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"}],"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\/10890611.pdf?arnumber=10890611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:31Z","timestamp":1774416331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890611","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}