{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:24:26Z","timestamp":1743103466793,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031209796"},{"type":"electronic","value":"9783031209802"}],"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\/978-3-031-20980-2_11","type":"book-chapter","created":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:03:09Z","timestamp":1668279789000},"page":"114-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Comparing Unsupervised Detection Algorithms for\u00a0Audio Adversarial Examples"],"prefix":"10.1007","author":[{"given":"Shanatip","family":"Choosaksakunwiboon","sequence":"first","affiliation":[]},{"given":"Karla","family":"Pizzi","sequence":"additional","affiliation":[]},{"given":"Ching-Yu","family":"Kao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Abdullah, H., Warren, K., Bindschaedler, V., Papernot, N., Traynor, P.: SoK: the faults in our ASRs: an overview of attacks against automatic speech recognition and speaker identification systems. In: 2021 IEEE Symposium on Security and Privacy (SP), pp. 730\u2013747. IEEE (2021)","DOI":"10.1109\/SP40001.2021.00014"},{"key":"11_CR2","unstructured":"Akinwande, V., Cintas, C., Speakman, S., Sridharan, S.: Identifying audio adversarial examples via anomalous pattern detection (2020)"},{"key":"11_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/978-3-030-60276-5_3","volume-title":"Speech and Computer","author":"I Andronic","year":"2020","unstructured":"Andronic, I., K\u00fcrzinger, L., Chavez Rosas, E.R., Rigoll, G., Seeber, B.U.: MP3 compression to diminish adversarial noise in end-to-end speech recognition. In: Karpov, A., Potapova, R. (eds.) SPECOM 2020. LNCS (LNAI), vol. 12335, pp. 22\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-60276-5_3"},{"key":"11_CR4","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: LREC 2020 (2020)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Audio adversarial examples: targeted attacks on speech-to-text. In: 2018 IEEE Security and Privacy Workshops (SPW), pp. 1\u20137. IEEE (2018)","DOI":"10.1109\/SPW.2018.00009"},{"key":"11_CR6","unstructured":"Das, N., et al.: Compression to the rescue: defending from adversarial attacks across modalities. In: KDD Project Showcase (2018)"},{"key":"11_CR7","unstructured":"Hussain, S., Neekhara, P., Dubnov, S., McAuley, J., Koushanfar, F.: WaveGuard: understanding and mitigating audio adversarial examples. In: USENIX Security 2021 (2021)"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes (2013). https:\/\/doi.org\/10.48550\/arxiv.1312.6114. https:\/\/arxiv.org\/abs\/1312.6114","DOI":"10.48550\/arxiv.1312.6114"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Liu, A., Yang, S., Chi, P.H., Hsu, P., Lee, H.: Mockingjay: unsupervised speech representation learning with deep bidirectional transformer encoders. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2020)","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"11_CR10","doi-asserted-by":"publisher","first-page":"2351","DOI":"10.1109\/TASLP.2021.3095662","volume":"29","author":"AT Liu","year":"2021","unstructured":"Liu, A.T., Li, S.W., Lee, H.: TERA: self-supervised learning of transformer encoder representation for speech. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 2351\u20132366 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413\u2013422 (2008)","DOI":"10.1109\/ICDM.2008.17"},{"key":"11_CR12","unstructured":"Mendes, E., Hogan, K.: Defending against imperceptible audio adversarial examples using proportional additive Gaussian noise (2020)"},{"key":"11_CR13","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1117\/1.1695413","volume":"13","author":"JL Mitchell","year":"2004","unstructured":"Mitchell, J.L.: Introduction to digital audio coding and standards. J. Electron. Imaging 13, 399 (2004)","journal-title":"J. Electron. Imaging"},{"key":"11_CR14","unstructured":"Mozilla: Project DeepSpeech (2021). https:\/\/github.com\/mozilla\/DeepSpeech"},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Olivier, R., Raj, B.: Recent improvements of ASR models in the face of adversarial attacks (2022). https:\/\/doi.org\/10.48550\/ARXIV.2203.16536. https:\/\/arxiv.org\/abs\/2203.16536","DOI":"10.48550\/ARXIV.2203.16536"},{"key":"11_CR16","doi-asserted-by":"publisher","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), pp. 5206\u20135210 (2015). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178964","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Park, N., Ji, S., Kim, J.: Detecting audio adversarial examples with logit noising. In: Proceedings of the 37th Annual Computer Security Applications Conference (ACSAC 2021) (2021)","DOI":"10.1145\/3485832.3485912"},{"key":"11_CR18","unstructured":"Paul, M.: An adversarial detection model for different data types. Master\u2019s thesis, Technical University of Munich (2021)"},{"key":"11_CR19","doi-asserted-by":"publisher","first-page":"579","DOI":"10.3390\/make2040031","volume":"2","author":"A Pereira","year":"2020","unstructured":"Pereira, A., Thomas, C.: Challenges of machine learning applied to safety-critical cyber-physical systems. Mach. Learn. Knowl. Extract. 2, 579\u2013602 (2020)","journal-title":"Mach. Learn. Knowl. Extract."},{"key":"11_CR20","unstructured":"Qin, Y., Carlini, N., Cottrell, G., Goodfellow, I., Raffel, C.: Imperceptible, robust, and targeted adversarial examples for automatic speech recognition. In: International Conference on Machine Learning, pp. 5231\u20135240. PMLR (2019)"},{"key":"11_CR21","unstructured":"Ravanelli, M., et al.: SpeechBrain: a general-purpose speech toolkit (2021). arXiv:2106.04624"},{"key":"11_CR22","unstructured":"Sch\u00f6lkopf, B., Williamson, R., Smola, A., Shawe-Taylor, J., Platt, J.: Support vector method for novelty detection. In: Neural Information Processing Systems 12 (NIPS 1999), vol. 12, pp. 582\u2013588 (1999)"},{"key":"11_CR23","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 (2018)","DOI":"10.14722\/ndss.2019.23288"},{"key":"11_CR24","unstructured":"Sperl, P., Kao, C., Chen, P., B\u00f6ttinger, K.: DLA: dense-layer-analysis for adversarial example detection. CoRR abs\/1911.01921 (2019). https:\/\/arxiv.org\/abs\/1911.01921"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Subramanian, V., Benetos, E., Sandler, M.B.: Robustness of adversarial attacks in sound event classification. In: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE 2019), pp. 239\u2013243 (2019)","DOI":"10.33682\/sp9n-qk06"},{"key":"11_CR26","unstructured":"Szurley, J., Kolter, J.Z.: Perceptual based adversarial audio attacks (2019)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Wu, H., Li, X., Liu, A.T., Wu, Z., Meng, H., Lee, H.: Adversarial defense for automatic speaker verification by cascaded self-supervised learning models. In: ICASSP 2021 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413737"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Wu, H., Liu, A., Lee, H.: Defense for black-box attacks on anti-spoofing models by self-supervised learning (2020)","DOI":"10.21437\/Interspeech.2020-2026"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Yakura, H., Sakuma, J.: Robust audio adversarial example for a physical attack. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (2018)","DOI":"10.24963\/ijcai.2019\/741"},{"key":"11_CR30","unstructured":"Yang, Z., Li, B., Chen, P.Y., Song, D.: Characterizing audio adversarial examples using temporal dependency (2019)"},{"key":"11_CR31","unstructured":"Yuan, X., et al.: CommanderSong: a systematic approach for practical adversarial voice recognition. In: USENIX Security 2018 (2018)"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, G., Yan, C., Ji, X., Zhang, T., Zhang, T., Xu, W.: DolphinAttack: inaudible voice commands. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (2017)","DOI":"10.1145\/3133956.3134052"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20980-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:04:15Z","timestamp":1668279855000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20980-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031209796","9783031209802"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20980-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gurugram","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"14 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.specom.co.in","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":"99","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":"60","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":"61% - 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":"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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}