{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:59:53Z","timestamp":1757624393205,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045485","type":"print"},{"value":"9783032045492","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04549-2_26","type":"book-chapter","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T13:48:40Z","timestamp":1757425720000},"page":"319-330","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TimbreAdv: Timbre Adversarial Attacks on\u00a0Speaker Verification Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3611-7294","authenticated-orcid":false,"given":"Ye","family":"Xiao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1014-9565","authenticated-orcid":false,"given":"Wenhan","family":"Yao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9231-8660","authenticated-orcid":false,"given":"Zexin","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4897-5157","authenticated-orcid":false,"given":"Jinsu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yuhao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xiandang","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Fen","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Weiping","family":"Wen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Bimbot, F., et al.: A tutorial on text-independent speaker verification. EURASIP J. Adv. Signal Process. 2004, 1\u201322 (2004)","DOI":"10.1155\/S1110865704310024"},{"key":"26_CR2","unstructured":"Goodfellow, I.J., et al.: Explaining and Harnessing Adversarial Examples. CoRR abs\/1412.6572 (2014)"},{"key":"26_CR3","unstructured":"Madry, A., et al.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Chen, P.-Y., et al.: Zoo: zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security (2017)","DOI":"10.1145\/3128572.3140448"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Adversarial attacks on GMM i-vector based speaker verification systems. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Villalba, J., Zhang, Y., Dehak, N.: x-vectors meet adversarial attacks: benchmarking adversarial robustness in speaker verification. In: Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-2458"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Luo, H., et al.: Spoofing speaker verification system by adversarial examples leveraging the generalized speaker difference. Secur. Commun. Netw. 2021(1), 6664578 (2021)","DOI":"10.1155\/2021\/6664578"},{"issue":"2","key":"26_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103242","volume":"60","author":"X Bi","year":"2023","unstructured":"Bi, X., et al.: Boosting question answering over knowledge graph with reward integration and policy evaluation under weak supervision. Inf. Process. Manag. 60(2), 103242 (2023)","journal-title":"Inf. Process. Manag."},{"key":"26_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2023.01.131","volume":"629","author":"J Liu","year":"2023","unstructured":"Liu, J., et al.: GNN-based long and short term preference modeling for next-location prediction. Inf. Sci. 629, 1\u201314 (2023)","journal-title":"Inf. Sci."},{"issue":"2","key":"26_CR10","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1049\/cit2.12186","volume":"8","author":"Y Jia","year":"2023","unstructured":"Jia, Y., et al.: Extrapolation over temporal knowledge graph via hyperbolic embedding. CAAI Trans. Intell. Technol. 8(2), 418\u2013429 (2023)","journal-title":"CAAI Trans. Intell. Technol."},{"issue":"6","key":"26_CR11","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: WavLM: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Lin, G.-T., et al.: On the utility of self-supervised models for prosody-related tasks. In: 2022 IEEE Spoken Language Technology Workshop (SLT). IEEE (2023)","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Zhao, X., et al.: Adversarial speaker disentanglement using unannotated external data for self-supervised representation-based voice conversion. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 1691\u20131696 (2023)","DOI":"10.1109\/ICME55011.2023.00291"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Feng, Y., et al.: Adversarial attack on deep product quantization network for image retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07 (2020)","DOI":"10.1609\/aaai.v34i07.6708"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Dual attention suppression attack: Generate adversarial camouflage in physical world. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00846"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Shamsabadi, A.S., et al.: Foolhd: fooling speaker identification by highly imperceptible adversarial disturbances. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413760"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Kreuk, F., et al.: Fooling end-to-end speaker verification with adversarial examples. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Xie, Y., et al.: Real-time, universal, and robust adversarial attacks against speaker recognition systems. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053747"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Attack on practical speaker verification system using universal adversarial perturbations. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413467"},{"key":"26_CR20","unstructured":"Chen, G., et al.: AS2T: arbitrary source-to-target adversarial attack on speaker recognition systems. IEEE Trans. Dependable Secure Comput. (2022)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Xie, Y., et al.: Enabling fast and universal audio adversarial attack using generative model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 16 (2021)","DOI":"10.1609\/aaai.v35i16.17663"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Universal adversarial perturbations generative network for speaker recognition. In: 2020 IEEE International Conference on Multimedia and Expo (ICME). IEEE (2020)","DOI":"10.1109\/ICME46284.2020.9102886"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Hanina, S., et al.: Universal adversarial attack against speaker recognition models. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447073"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Panayotov, V., et al.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: Deep Speaker Recognition (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"26_CR27","unstructured":"Radford, A., et al.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning. PMLR (2023)"},{"key":"26_CR28","first-page":"17022","volume":"33","author":"J Kong","year":"2020","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. Adv. Neural. Inf. Process. Syst. 33, 17022\u201317033 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Eres2netv2: boosting short-duration speaker verification performance with computational efficiency. arXiv preprint arXiv:2406.02167 (2024)","DOI":"10.21437\/Interspeech.2024-742"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Zolfi, A., et al.: Adversarial mask: real-world universal adversarial attack on face recognition models. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-26409-2_19"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04549-2_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T13:48:56Z","timestamp":1757425736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04549-2_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"ISBN":["9783032045485","9783032045492"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04549-2_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"assertion":[{"value":"10 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}