{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T20:37:13Z","timestamp":1759091833442,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T00:00:00Z","timestamp":1638748800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and communications Technology Promotion","doi-asserted-by":"publisher","award":["2018-0-01392, 2018-0-01441"],"award-info":[{"award-number":["2018-0-01392, 2018-0-01441"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,12,6]]},"DOI":"10.1145\/3485832.3485912","type":"proceedings-article","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T13:42:32Z","timestamp":1638798152000},"page":"586-595","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Detecting Audio Adversarial Examples with Logit Noising"],"prefix":"10.1145","author":[{"given":"Namgyu","family":"Park","sequence":"first","affiliation":[{"name":"POSTECH, Korea, South - Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangwoo","family":"Ji","sequence":"additional","affiliation":[{"name":"POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong","family":"Kim","sequence":"additional","affiliation":[{"name":"POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,12,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mart\u00edn Abadi 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/ Software available from tensorflow.org."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00009"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Hadi Abdullah Kevin Warren Vincent Bindschaedler Nicolas Papernot and Patrick Traynor. 2020. SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems. arxiv:2007.06622\u00a0[cs.CR]","DOI":"10.1109\/SP40001.2021.00014"},{"key":"e_1_3_2_1_4_1","volume-title":"Discrete cosine transform","author":"Ahmed Nasir","year":"1974","unstructured":"Nasir Ahmed, T_ Natarajan, and Kamisetty\u00a0R Rao. 1974. Discrete cosine transform. IEEE transactions on Computers 100, 1 (1974), 90\u201393."},{"key":"e_1_3_2_1_5_1","unstructured":"\u201dAmazon\u201d. [n. d.]. \u201dAmazon Alexa\u201d. https:\/\/www.amazon.com."},{"key":"e_1_3_2_1_6_1","unstructured":"\u201dApple\u201d. [n. d.]. \u201dApple Siri\u201d. https:\/\/www.apple.com\/siri."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a080)","author":"Athalye Anish","year":"2018","unstructured":"Anish Athalye, Logan Engstrom, Andrew Ilyas, and Kevin Kwok. 2018. Synthesizing Robust Adversarial Examples. In Proceedings of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a080), Jennifer Dy and Andreas Krause (Eds.). PMLR, 284\u2013293. http:\/\/proceedings.mlr.press\/v80\/athalye18b.html"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2020.23055"},{"key":"e_1_3_2_1_10_1","volume-title":"29th USENIX Security Symposium (USENIX Security 20)","author":"Chen Yuxuan","year":"2020","unstructured":"Yuxuan Chen, Xuejing Yuan, Jiangshan Zhang, Yue Zhao, Shengzhi Zhang, Kai Chen, and XiaoFeng Wang. 2020. Devil\u2019s Whisper: A General Approach for Physical Adversarial Attacks against Commercial Black-box Speech Recognition Devices. In 29th USENIX Security Symposium (USENIX Security 20). USENIX Association, 2667\u20132684. https:\/\/www.usenix.org\/conference\/usenixsecurity20\/presentation\/chen-yuxuan"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385003.3410921"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413603"},{"key":"e_1_3_2_1_13_1","unstructured":"\u201dGoogle\u201d. [n. d.]. \u201dGoogle Assistant\u201d. https:\/\/assistant.google.com."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_1_15_1","volume-title":"Deep Speech: Scaling up end-to-end speech recognition. arxiv:1412.5567\u00a0[cs.CL]","author":"Hannun Awni","year":"2014","unstructured":"Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, and Andrew\u00a0Y. Ng. 2014. Deep Speech: Scaling up end-to-end speech recognition. arxiv:1412.5567\u00a0[cs.CL]"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363246"},{"volume-title":"Soviet physics doklady, Vol.\u00a010","author":"Levenshtein I","key":"e_1_3_2_1_17_1","unstructured":"Vladimir\u00a0I Levenshtein. 1966. Binary codes capable of correcting deletions, insertions, and reversals. In Soviet physics doklady, Vol.\u00a010. Soviet Union, 707\u2013710."},{"key":"e_1_3_2_1_18_1","unstructured":"Juncheng\u00a0B Li Shuhui Qu Xinjian Li Joseph Szurley J\u00a0Zico Kolter and Florian Metze. 2019. Adversarial music: Real world audio adversary against wake-word detection system. arXiv preprint arXiv:1911.00126(2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3025"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3423348"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5928"},{"key":"e_1_3_2_1_22_1","unstructured":"Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras and Adrian Vladu. 2017. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083(2017)."},{"key":"e_1_3_2_1_23_1","unstructured":"\u201dMicrosoft\u201d. [n. d.]. \u201dMicrosoft Cortana\u201d. https:\/\/www.microsoft.com\/en-us\/cortana."},{"key":"e_1_3_2_1_24_1","unstructured":"Lindasalwa Muda Mumtaj Begam and Irraivan Elamvazuthi. 2010. Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. arXiv preprint arXiv:1003.4083(2010)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_26_1","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society.","author":"Povey Daniel","year":"2011","unstructured":"Daniel Povey, Arnab Ghoshal, Gilles Boulianne, Lukas Burget, Ondrej Glembek, Nagendra Goel, Mirko Hannemann, Petr Motlicek, Yanmin Qian, Petr Schwarz, 2011. The Kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097)","author":"Qin Yao","year":"2019","unstructured":"Yao Qin, Nicholas Carlini, Garrison Cottrell, Ian Goodfellow, and Colin Raffel. 2019. Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 5231\u20135240. http:\/\/proceedings.mlr.press\/v97\/qin19a.html"},{"key":"e_1_3_2_1_28_1","unstructured":"Lawrence\u00a0R Rabiner Ronald\u00a0W Schafer 1978. Digital processing of speech signals. Prentice-hall."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427228.3427276"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Lea Sch\u00f6nherr Katharina Kohls Steffen Zeiler Thorsten Holz and Dorothea Kolossa. 2018. Adversarial attacks against automatic speech recognition systems via psychoacoustic hiding. arXiv preprint arXiv:1808.05665(2018).","DOI":"10.14722\/ndss.2019.23288"},{"key":"e_1_3_2_1_31_1","unstructured":"Jonathan Shen and et. al.2019. Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling. CoRR abs\/1902.08295(2019). arxiv:1902.08295http:\/\/arxiv.org\/abs\/1902.08295"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00016"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683479"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/741"},{"key":"e_1_3_2_1_35_1","volume-title":"Characterizing Audio Adversarial Examples Using Temporal Dependency. In International Conference on Learning Representations.","author":"Yang Zhuolin","year":"2018","unstructured":"Zhuolin Yang, Bo Li, Pin-Yu Chen, and Dawn Song. 2018. Characterizing Audio Adversarial Examples Using Temporal Dependency. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","volume-title":"Commandersong: A systematic approach for practical adversarial voice recognition. In 27th {USENIX} Security Symposium ({USENIX} Security 18). 49\u201364.","author":"Yuan Xuejing","year":"2018","unstructured":"Xuejing Yuan, Yuxuan Chen, Yue Zhao, Yunhui Long, Xiaokang Liu, Kai Chen, Shengzhi Zhang, Heqing Huang, Xiaofeng Wang, and Carl\u00a0A Gunter. 2018. Commandersong: A systematic approach for practical adversarial voice recognition. In 27th {USENIX} Security Symposium ({USENIX} Security 18). 49\u201364."}],"event":{"name":"ACSAC '21: Annual Computer Security Applications Conference","acronym":"ACSAC '21","location":"Virtual Event USA"},"container-title":["Annual Computer Security Applications Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485832.3485912","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485832.3485912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:15:37Z","timestamp":1755890137000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485832.3485912"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,6]]},"references-count":36,"alternative-id":["10.1145\/3485832.3485912","10.1145\/3485832"],"URL":"https:\/\/doi.org\/10.1145\/3485832.3485912","relation":{},"subject":[],"published":{"date-parts":[[2021,12,6]]},"assertion":[{"value":"2021-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}