{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:53:04Z","timestamp":1769633584872,"version":"3.49.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031212796","type":"print"},{"value":"9783031212802","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-21280-2_26","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T08:30:15Z","timestamp":1668760215000},"page":"468-484","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Practical Backdoor Attack Against Speaker Recognition System"],"prefix":"10.1007","author":[{"given":"Yuxiao","family":"Luo","sequence":"first","affiliation":[]},{"given":"Jianwei","family":"Tai","sequence":"additional","affiliation":[]},{"given":"Xiaoqi","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Shengzhi","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"26_CR1","unstructured":"Agarap, A.F.: Deep learning using rectified linear units (ReLU). arXiv preprint arXiv:1803.08375 (2018)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Bhattacharya, G., Alam, M.J., Kenny, P.: Deep speaker recognition: modular or monolithic? In: INTERSPEECH, pp. 1143\u20131147 (2019)","DOI":"10.21437\/Interspeech.2019-3146"},{"key":"26_CR3","unstructured":"Chen, X., Liu, C., Li, B., Lu, K., Song, D.: Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526 (2017)"},{"key":"26_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/11856214_4","volume-title":"Recent Advances in Intrusion Detection","author":"SP Chung","year":"2006","unstructured":"Chung, S.P., Mok, A.K.: Allergy attack against automatic signature generation. In: Zamboni, D., Kruegel, C. (eds.) RAID 2006. LNCS, vol. 4219, pp. 61\u201380. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11856214_4"},{"key":"26_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1007\/978-3-540-74320-0_13","volume-title":"Recent Advances in Intrusion Detection","author":"SP Chung","year":"2007","unstructured":"Chung, S.P., Mok, A.K.: Advanced allergy attacks: does a corpus really help? In: Kruegel, C., Lippmann, R., Clark, A. (eds.) RAID 2007. LNCS, vol. 4637, pp. 236\u2013255. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74320-0_13"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Conneau, A., Schwenk, H., Barrault, L., Lecun, Y.: Very deep convolutional networks for text classification. arXiv preprint arXiv:1606.01781 (2016)","DOI":"10.18653\/v1\/E17-1104"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Dalvi, N., Domingos, P., Sanghai, S., Verma, D.: Adversarial classification. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 99\u2013108 (2004)","DOI":"10.1145\/1014052.1014066"},{"issue":"4","key":"26_CR8","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"1","key":"26_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc.: Ser. B (Methodol.) 39(1), 1\u201322 (1977)","journal-title":"J. Roy. Stat. Soc.: Ser. B (Methodol.)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Fortuna, J., Sivakumaran, P., Ariyaeeinia, A., Malegaonkar, A.: Open-set speaker identification using adapted Gaussian mixture models. In: Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-627"},{"key":"26_CR11","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"key":"26_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"26_CR13","unstructured":"Gu, T., Dolan-Gavitt, B., Garg, S.: BadNets: identifying vulnerabilities in the machine learning model supply chain. arXiv preprint arXiv:1708.06733 (2017)"},{"key":"26_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/3-540-59497-3_175","volume-title":"From Natural to Artificial Neural Computation","author":"J Han","year":"1995","unstructured":"Han, J., Moraga, C.: The influence of the sigmoid function parameters on the speed of backpropagation learning. In: Mira, J., Sandoval, F. (eds.) IWANN 1995. LNCS, vol. 930, pp. 195\u2013201. Springer, Heidelberg (1995). https:\/\/doi.org\/10.1007\/3-540-59497-3_175"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning. Image Recogn. 7 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Huang, L., Joseph, A.D., Nelson, B., Rubinstein, B.I., Tygar, J.D.: Adversarial machine learning. In: Proceedings of the 4th ACM Workshop on Security and Artificial Intelligence, pp. 43\u201358 (2011)","DOI":"10.1145\/2046684.2046692"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Y.Y., Wang, W.Y.: Deep residual learning for weakly-supervised relation extraction. arXiv preprint arXiv:1707.08866 (2017)","DOI":"10.18653\/v1\/D17-1191"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Koffas, S., Xu, J., Conti, M., Picek, S.: Can you hear it? Backdoor attacks via ultrasonic triggers. arXiv preprint arXiv:2107.14569 (2021)","DOI":"10.1145\/3522783.3529523"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Lowd, D., Meek, C.: Adversarial learning. In: Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, pp. 641\u2013647 (2005)","DOI":"10.1145\/1081870.1081950"},{"key":"26_CR20","unstructured":"Lowd, D., Meek, C.: Good word attacks on statistical spam filters. In: CEAS, vol. 2005 (2005)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"McLaren, M., Ferrer, L., Castan, D., Lawson, A.: The speakers in the wild (SITW) speaker recognition database. In: Interspeech, pp. 818\u2013822 (2016)","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"26_CR22","unstructured":"Muda, L., Begam, M., Elamvazuthi, I.: Voice recognition algorithms using Mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. arXiv preprint arXiv:1003.4083 (2010)"},{"key":"26_CR23","unstructured":"Multimodal Information Group (2022). https:\/\/www.nist.gov\/itl\/iad\/mig\/speaker-recognition"},{"key":"26_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"Nagrani, A., Chung, J.S., Xie, W., Zisserman, A.: VoxCeleb: large-scale speaker verification in the wild. Comput. Speech Lang. 60, 101027 (2020)","journal-title":"Comput. Speech Lang."},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Nandwana, M.K., Ferrer, L., McLaren, M., Castan, D., Lawson, A.: Analysis of critical metadata factors for the calibration of speaker recognition systems. In: INTERSPEECH, pp. 4325\u20134329 (2019)","DOI":"10.21437\/Interspeech.2019-1808"},{"key":"26_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/11856214_5","volume-title":"Recent Advances in Intrusion Detection","author":"J Newsome","year":"2006","unstructured":"Newsome, J., Karp, B., Song, D.: Paragraph: thwarting signature learning by training maliciously. In: Zamboni, D., Kruegel, C. (eds.) RAID 2006. LNCS, vol. 4219, pp. 81\u2013105. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11856214_5"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A.: Gaussian mixture models. Encyclopedia Biometrics 741(659\u2013663) (2009)","DOI":"10.1007\/978-0-387-73003-5_196"},{"issue":"1\u20133","key":"26_CR28","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted Gaussian mixture models. Digit. Signal Process. 10(1\u20133), 19\u201341 (2000)","journal-title":"Digit. Signal Process."},{"issue":"1","key":"26_CR29","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/89.365379","volume":"3","author":"DA Reynolds","year":"1995","unstructured":"Reynolds, D.A., Rose, R.C.: Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. Speech Audio Process. 3(1), 72\u201383 (1995)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Saha, A., Subramanya, A., Pirsiavash, H.: Hidden trigger backdoor attacks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11957\u201311965 (2020)","DOI":"10.1609\/aaai.v34i07.6871"},{"key":"26_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., McCree, A., Povey, D., Khudanpur, S.: Speaker recognition for multi-speaker conversations using X-vectors. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 5796\u20135800. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: robust DNN embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"26_CR34","unstructured":"Turner, A., Tsipras, D., Madry, A.: Clean-label backdoor attacks (2018)"},{"key":"26_CR35","unstructured":"Wittel, G.L., Wu, S.F.: On attacking statistical spam filters. In: CEAS. Citeseer (2004)"},{"key":"26_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1007\/978-3-540-30543-9_71","volume-title":"Advances in Multimedia Information Processing - PCM 2004","author":"M Xu","year":"2004","unstructured":"Xu, M., Duan, L.-Y., Cai, J., Chia, L.-T., Xu, C., Tian, Q.: HMM-based audio keyword generation. In: Aizawa, K., Nakamura, Y., Satoh, S. (eds.) PCM 2004. LNCS, vol. 3333, pp. 566\u2013574. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-30543-9_71"},{"issue":"12","key":"26_CR37","doi-asserted-by":"publisher","first-page":"5786","DOI":"10.3390\/app12125786","volume":"12","author":"J Ye","year":"2022","unstructured":"Ye, J., Liu, X., You, Z., Li, G., Liu, B.: DriNet: dynamic backdoor attack against automatic speech recognization models. Appl. Sci. 12(12), 5786 (2022)","journal-title":"Appl. Sci."},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Zhai, T., Li, Y., Zhang, Z.M., Wu, B., Jiang, Y., Xia, S.: Backdoor attack against speaker verification. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2560\u20132564 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413468"}],"container-title":["Lecture Notes in Computer Science","Information Security Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21280-2_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T01:13:15Z","timestamp":1728436395000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21280-2_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031212796","9783031212802"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21280-2_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISPEC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information Security Practice and Experience","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ispec2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ispec2022.ndhu.edu.tw\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"87","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2 invited papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}