{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:37:43Z","timestamp":1767983863793,"version":"3.49.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030880514","type":"print"},{"value":"9783030880521","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-88052-1_9","type":"book-chapter","created":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:49:44Z","timestamp":1631839784000},"page":"142-160","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Black-Box Audio Adversarial Example Generation Using Variational Autoencoder"],"prefix":"10.1007","author":[{"given":"Wei","family":"Zong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3348-7014","authenticated-orcid":false,"given":"Yang-Wai","family":"Chow","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1562-5105","authenticated-orcid":false,"given":"Willy","family":"Susilo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,17]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Abdullah, H., et al.: Hear \u201cno evil\u201d, see \u201ckenansville\u201d: efficient and transferable black-box attacks on speech recognition and voice identification systems. In: 2021 IEEE Symposium on Security and Privacy (SP), Los Alamitos, CA, USA, May 2021, pp. 142\u2013159. IEEE Computer Society (2021)","DOI":"10.1109\/SP40001.2021.00009"},{"key":"9_CR2","unstructured":"Alzantot, M., Balaji, B., Srivastava, M.B.: Did you hear that? Adversarial examples against automatic speech recognition. CoRR, abs\/1801.00554 (2018)"},{"key":"9_CR3","unstructured":"Athalye, A., Engstrom, L., Ilyas, A., Kwok, K.: Synthesizing robust adversarial examples. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 July 2018, pp. 284\u2013293 (2018)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.A.: Audio adversarial examples: targeted attacks on speech-to-text. In: 2018 IEEE Security and Privacy Workshops, SP Workshops 2018, San Francisco, CA, USA, 24 May 2018, pp. 1\u20137 (2018)","DOI":"10.1109\/SPW.2018.00009"},{"key":"9_CR5","unstructured":"Chen, G., et al.: Who is real bob? Adversarial attacks on speaker recognition systems. CoRR, abs\/1911.01840 (2019)"},{"key":"9_CR6","unstructured":"Ciss\u00e9, M., Adi, Y., Neverova, N., Keshet, J.: Houdini: fooling deep structured visual and speech recognition models with adversarial examples. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, 4\u20139 December 2017, pp. 6977\u20136987 (2017)"},{"key":"9_CR7","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F.J., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Machine Learning, Proceedings of the Twenty-Third International Conference (ICML 2006), Pittsburgh, Pennsylvania, USA, 25\u201329 June 2006, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"issue":"2","key":"9_CR9","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/TASSP.1984.1164317","volume":"32","author":"D Griffin","year":"1984","unstructured":"Griffin, D., Lim, J.: Signal estimation from modified short-time Fourier transform. IEEE Trans. Acoust. Speech Signal Process. 32(2), 236\u2013243 (1984)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"9_CR10","unstructured":"Hannun, A.Y., et al.: Deep speech: scaling up end-to-end speech recognition. CoRR, abs\/1412.5567 (2014)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Hsu, W., Zhang, Y., Glass, J.R.: Learning latent representations for speech generation and transformation. In: Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, 20\u201324 August 2017, pp. 1273\u20131277 (2017)","DOI":"10.21437\/Interspeech.2017-349"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Khare, S., Aralikatte, R., Mani, S.: Adversarial black-box attacks for automatic speech recognition systems using multi-objective genetic optimization. CoRR, abs\/1811.01312 (2018)","DOI":"10.21437\/Interspeech.2019-2420"},{"key":"9_CR13","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014)"},{"key":"9_CR14","unstructured":"Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Workshop Track Proceedings (2017)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Lugosch, L., Ravanelli, M., Ignoto, P., Tomar, V.S., Bengio, Y.: Speech model pre-training for end-to-end spoken language understanding. CoRR, abs\/1904.03670 (2019)","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 86\u201394 (2017)","DOI":"10.1109\/CVPR.2017.17"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: LibriSpeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, South Brisbane, Queensland, Australia, 19\u201324 April 2015, pp. 5206\u20135210 (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"9_CR18","unstructured":"Qin, Y., Carlini, N., Cottrell, G.W., Goodfellow, I.J., Raffel, C.: Imperceptible, robust, and targeted adversarial examples for automatic speech recognition. In: Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, California, USA, 9\u201315 June 2019, pp. 5231\u20135240 (2019)"},{"key":"9_CR19","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M.P., Hekstra, A.P.: Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2001, Salt Palace Convention Center, Salt Lake City, Utah, USA, 7\u201311 May, 2001, Proceedings, pp. 749\u2013752. IEEE (2001)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nherr, L., Kohls, K., Zeiler, S., Holz, T., Kolossa, D.: Adversarial attacks against automatic speech recognition systems via psychoacoustic hiding. In: 26th Annual Network and Distributed System Security Symposium, NDSS 2019, San Diego, California, USA, 24\u201327 February 2019 (2019)","DOI":"10.14722\/ndss.2019.23288"},{"key":"9_CR21","unstructured":"Szegedy, C., et al.: Intriguing properties of neural networks. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Taori, R., Kamsetty, A., Chu, B., Vemuri, N.: Targeted adversarial examples for black box audio systems. In: 2019 IEEE Security and Privacy Workshops, SP Workshops 2019, San Francisco, CA, USA, 19\u201323 May 2019, pp. 15\u201320 (2019)","DOI":"10.1109\/SPW.2019.00016"},{"key":"9_CR23","unstructured":"van den Oord, A., et al.: WaveNet: a generative model for raw audio. In: The 9th ISCA Speech Synthesis Workshop, Sunnyvale, CA, USA, 13\u201315 September 2016, p. 125 (2016)"},{"key":"9_CR24","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/TIFS.2020.3026543","volume":"16","author":"Q Wang","year":"2021","unstructured":"Wang, Q., Zheng, B., Li, Q., Shen, C., Ba, Z.: Towards query-efficient adversarial attacks against automatic speech recognition systems. IEEE Trans. Inf. Forensics Secur. 16, 896\u2013908 (2021)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"9_CR25","unstructured":"Yang, Z., Li, B., Chen, P., Song, D.: Characterizing audio adversarial examples using temporal dependency. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019 (2019)"}],"container-title":["Lecture Notes in Computer Science","Information and Communications Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88052-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T13:47:51Z","timestamp":1725803271000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88052-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030880514","9783030880521"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88052-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"17 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICICS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information and Communications Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chongqing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icics2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icics.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"182","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":"49","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":"27% - 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":"4","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":"5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}