{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T15:15:36Z","timestamp":1788448536663,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S. ARO","award":["W911NF-17-1-0447"],"award-info":[{"award-number":["W911NF-17-1-0447"]}]},{"name":"U.S. ONR","award":["N00014-16-1-3214"],"award-info":[{"award-number":["N00014-16-1-3214"]}]},{"name":"U.S. ONR","award":["N00014-18-2893"],"award-info":[{"award-number":["N00014-18-2893"]}]},{"name":"NSFC","award":["61572278"],"award-info":[{"award-number":["61572278"]}]},{"name":"NSFC","award":["U1736209"],"award-info":[{"award-number":["U1736209"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,30]]},"DOI":"10.1145\/3372297.3417254","type":"proceedings-article","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T18:27:04Z","timestamp":1604341624000},"page":"1103-1119","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["When the Differences in Frequency Domain are Compensated: Understanding and Defeating Modulated Replay Attacks on Automatic Speech Recognition"],"prefix":"10.1145","author":[{"given":"Shu","family":"Wang","sequence":"first","affiliation":[{"name":"George Mason University, Fairfax, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Cao","sequence":"additional","affiliation":[{"name":"George Mason University & Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"He","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Sun","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,11,2]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23362"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2747626"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2747626"},{"key":"e_1_3_2_2_4_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Amazon_Alexa, [accessed","author":"Alexa Amazon","year":"2018","unstructured":"Amazon Alexa . 2018. Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Amazon_Alexa, [accessed December 2018 ]. Amazon Alexa. 2018. Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Amazon_Alexa, [accessed December 2018]."},{"key":"e_1_3_2_2_5_1","volume-title":"https:\/\/assistant.google.com\/, [accessed","author":"Assistant Google","year":"2019","unstructured":"Google Assistant . 2019. Google. https:\/\/assistant.google.com\/, [accessed December 2019 ]. Google Assistant. 2019. Google. https:\/\/assistant.google.com\/, [accessed December 2019]."},{"key":"e_1_3_2_2_6_1","volume-title":"Voiceprint: The New WeChat Password. https:\/\/www.techinasia.com\/baidu-lenovo-voice-recognition-android-unlock, [Accessed","author":"WeChat Blog The Offical","year":"2019","unstructured":"The Offical WeChat Blog . 2019 . Voiceprint: The New WeChat Password. https:\/\/www.techinasia.com\/baidu-lenovo-voice-recognition-android-unlock, [Accessed September, 2019]. The Offical WeChat Blog. 2019. Voiceprint: The New WeChat Password. https:\/\/www.techinasia.com\/baidu-lenovo-voice-recognition-android-unlock, [Accessed September, 2019]."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196494.3196545"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3212480.3212505"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2245650"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2158420"},{"key":"e_1_3_2_2_11_1","volume-title":"Hidden Voice Commands. In 25th USENIX Security Symposium (USENIX Security 16)","author":"Carlini Nicholas","year":"2016","unstructured":"Nicholas Carlini , Pratyush Mishra , Tavish Vaidya , Yuankai Zhang , Micah Sherr , Clay Shields , David Wagner , and Wenchao Zhou . 2016 . Hidden Voice Commands. In 25th USENIX Security Symposium (USENIX Security 16) . USENIX Association, Austin, TX, 513--530. https:\/\/www.usenix.org\/conference\/usenixsecurity16\/technical-sessions\/presentation\/carlini Nicholas Carlini, Pratyush Mishra, Tavish Vaidya, Yuankai Zhang, Micah Sherr, Clay Shields, David Wagner, and Wenchao Zhou. 2016. Hidden Voice Commands. In 25th USENIX Security Symposium (USENIX Security 16). USENIX Association, Austin, TX, 513--530. https:\/\/www.usenix.org\/conference\/usenixsecurity16\/technical-sessions\/presentation\/carlini"},{"key":"e_1_3_2_2_12_1","volume-title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In 2018 IEEE Security and Privacy Workshops (SPW). 1--7.","author":"Carlini N.","unstructured":"N. Carlini and D. Wagner . 2018 . Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In 2018 IEEE Security and Privacy Workshops (SPW). 1--7. N. Carlini and D. Wagner. 2018. Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In 2018 IEEE Security and Privacy Workshops (SPW). 1--7."},{"key":"e_1_3_2_2_13_1","volume-title":"Applied Sciences","volume":"8","author":"Cecchi Stefania","year":"2018","unstructured":"Stefania Cecchi , Alberto Carini , and Sascha Spors . 2018 . Room Response Equalization?A Review . Applied Sciences , Vol. 8 , 1 (2018). https:\/\/doi.org\/10.3390\/app8010016 10.3390\/app8010016 Stefania Cecchi, Alberto Carini, and Sascha Spors. 2018. Room Response Equalization?A Review. Applied Sciences, Vol. 8, 1 (2018). https:\/\/doi.org\/10.3390\/app8010016"},{"key":"e_1_3_2_2_14_1","volume-title":"https:\/\/www.microsoft.com\/en-us\/cortana, [accessed","author":"Cortana Microsoft","year":"2019","unstructured":"Microsoft Cortana . 2019. Microsoft. https:\/\/www.microsoft.com\/en-us\/cortana, [accessed December 2019 ]. Microsoft Cortana. 2019. Microsoft. https:\/\/www.microsoft.com\/en-us\/cortana, [accessed December 2019]."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2201472"},{"key":"e_1_3_2_2_16_1","volume-title":"21st European Signal Processing Conference (EUSIPCO","author":"Defraene B.","year":"2013","unstructured":"B. Defraene , T. van Waterschoot , M. Diehl , and M. Moonen . 2013. Embedded-optimization-based loudspeaker compensation using a generic Hammerstein loudspeaker model . In 21st European Signal Processing Conference (EUSIPCO 2013 ). 1--5. B. Defraene, T. van Waterschoot, M. Diehl, and M. Moonen. 2013. Embedded-optimization-based loudspeaker compensation using a generic Hammerstein loudspeaker model. In 21st European Signal Processing Conference (EUSIPCO 2013). 1--5."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2666620.2666623"},{"key":"e_1_3_2_2_18_1","volume-title":"Crafting Adversarial Examples For Speech Paralinguistics Applications. CoRR","author":"Gong Yuan","year":"2017","unstructured":"Yuan Gong and Christian Poellabauer . 2017. Crafting Adversarial Examples For Speech Paralinguistics Applications. CoRR , Vol. abs\/ 1711 .03280 ( 2017 ). arxiv: 1711.03280 http:\/\/arxiv.org\/abs\/1711.03280 Yuan Gong and Christian Poellabauer. 2017. Crafting Adversarial Examples For Speech Paralinguistics Applications. CoRR, Vol. abs\/1711.03280 (2017). arxiv: 1711.03280 http:\/\/arxiv.org\/abs\/1711.03280"},{"key":"#cr-split#-e_1_3_2_2_19_1.1","doi-asserted-by":"crossref","unstructured":"Y. Gong and C. Poellabauer. 2018. Protecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues. In 2018 27th International Conference on Computer Communication and Networks (ICCCN). 1--9. https:\/\/doi.org\/10.1109\/ICCCN.2018.8487334 10.1109\/ICCCN.2018.8487334","DOI":"10.1109\/ICCCN.2018.8487334"},{"key":"#cr-split#-e_1_3_2_2_19_1.2","doi-asserted-by":"crossref","unstructured":"Y. Gong and C. Poellabauer. 2018. Protecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues. In 2018 27th International Conference on Computer Communication and Networks (ICCCN). 1--9. https:\/\/doi.org\/10.1109\/ICCCN.2018.8487334","DOI":"10.1109\/ICCCN.2018.8487334"},{"key":"e_1_3_2_2_20_1","volume-title":"Accessed","year":"2019","unstructured":"Google. 2019 . Let \"Ok Google\" and \"Hey Google\" unlock your phone or tablet. https:\/\/support.google.com\/assistant\/answer\/7394306?co=GENIE.Platform%3DAndroid&hl=en . Accessed September, 2019. Google. 2019. Let \"Ok Google\" and \"Hey Google\" unlock your phone or tablet. https:\/\/support.google.com\/assistant\/answer\/7394306?co=GENIE.Platform%3DAndroid&hl=en. Accessed September, 2019."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1473"},{"key":"e_1_3_2_2_22_1","volume-title":"I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry. In INTERSPEECH.","author":"Rosa Gonz\u00e1lez","year":"2013","unstructured":"Rosa Gonz\u00e1lez Hautam\"aki, Tomi Kinnunen , Ville Hautam\"aki, Timo Leino , and Anne-Maria Laukkanen . 2013 . I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry. In INTERSPEECH. Rosa Gonz\u00e1lez Hautam\"aki, Tomi Kinnunen, Ville Hautam\"aki, Timo Leino, and Anne-Maria Laukkanen. 2013. I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry. In INTERSPEECH."},{"key":"e_1_3_2_2_23_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/44,100_Hz. [accessed","author":"Wikipedia Hz.","year":"2019","unstructured":"44100 Hz. 2019. Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/44,100_Hz. [accessed November 2019 ]. 44100 Hz. 2019. Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/44,100_Hz. [accessed November 2019]."},{"key":"e_1_3_2_2_24_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Spline_interpolation, [accessed","author":"Wikipedia Spline","year":"2019","unstructured":"Spline interpolation. 2019. Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Spline_interpolation, [accessed April 2019 ]. Spline interpolation. 2019. Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Spline_interpolation, [accessed April 2019]."},{"key":"e_1_3_2_2_25_1","volume-title":"Biometrics: personal identification in networked society","author":"Jain Anil K","unstructured":"Anil K Jain , Ruud Bolle , and Sharath Pankanti . 2006. Biometrics: personal identification in networked society . Vol. 479 . Springer Science & Business Media . Anil K Jain, Ruud Bolle, and Sharath Pankanti. 2006. Biometrics: personal identification in networked society. Vol. 479. Springer Science & Business Media."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660295"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081178"},{"key":"e_1_3_2_2_28_1","volume-title":"Novel Amplitude Weighted Frequency Modulation Features for Replay Spoof Detection. In 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP). 185--189","author":"Kamble M. R.","year":"2018","unstructured":"M. R. Kamble and H. A. Patil . 2018 . Novel Amplitude Weighted Frequency Modulation Features for Replay Spoof Detection. In 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP). 185--189 . https:\/\/doi.org\/10.1109\/ISCSLP. 2018 .8706673 10.1109\/ISCSLP.2018.8706673 M. R. Kamble and H. A. Patil. 2018. Novel Amplitude Weighted Frequency Modulation Features for Replay Spoof Detection. In 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP). 185--189. https:\/\/doi.org\/10.1109\/ISCSLP.2018.8706673"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288895"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3277203.3277207"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363246"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-360"},{"key":"e_1_3_2_2_34_1","unstructured":"Phillip L. De Leon Bryan Stewart and Junichi Yamagishi. 2012. Synthetic Speech Discrimination using Pitch Pattern Statistics Derived from Image Analysis. In INTERSPEECH.  Phillip L. De Leon Bryan Stewart and Junichi Yamagishi. 2012. Synthetic Speech Discrimination using Pitch Pattern Statistics Derived from Image Analysis. In INTERSPEECH."},{"key":"e_1_3_2_2_35_1","unstructured":"Dongbo Li Longbiao Wang Jianwu Dang Meng Liu Zeyan Oo Seiichi Nakagawa Haotian Guan and Xiangang Li. 2018. Multiple Phase Information Combination for Replay Attacks Detection. In INTERSPEECH.  Dongbo Li Longbiao Wang Jianwu Dang Meng Liu Zeyan Oo Seiichi Nakagawa Haotian Guan and Xiangang Li. 2018. Multiple Phase Information Combination for Replay Attacks Detection. In INTERSPEECH."},{"key":"e_1_3_2_2_36_1","volume-title":"Accessed","author":"Lieu Johnny","year":"2019","unstructured":"Johnny Lieu . 2019 . Volkswagen drivers can unlock their cars with Siri. https:\/\/mashable.com\/article\/volkswagen-siri-shortcuts-unlock\/ . Accessed September, 2019. Johnny Lieu. 2019. Volkswagen drivers can unlock their cars with Siri. https:\/\/mashable.com\/article\/volkswagen-siri-shortcuts-unlock\/. Accessed September, 2019."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICALIP.2012.6376608"},{"key":"e_1_3_2_2_38_1","volume-title":"Towards Vulnerability Analysis of Voice-Driven Interfaces and Countermeasures for Replay Attacks. In 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). 523--528","author":"Malik K. M.","year":"2019","unstructured":"K. M. Malik , H. Malik , and R. Baumann . 2019 . Towards Vulnerability Analysis of Voice-Driven Interfaces and Countermeasures for Replay Attacks. In 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). 523--528 . https:\/\/doi.org\/10.1109\/MIPR. 2019 .00106 10.1109\/MIPR.2019.00106 K. M. Malik, H. Malik, and R. Baumann. 2019. Towards Vulnerability Analysis of Voice-Driven Interfaces and Countermeasures for Replay Attacks. In 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). 523--528. https:\/\/doi.org\/10.1109\/MIPR.2019.00106"},{"key":"e_1_3_2_2_39_1","volume-title":"Open Sesame: Baidu Helps Lenovo Use Voice Recognition to Unlock Android Phones. https:\/\/www.techinasia.com\/baidu-lenovo-voice-recognition-android-unlock, [Accessed","author":"Millward Steven","year":"2019","unstructured":"Steven Millward . 2019 . Open Sesame: Baidu Helps Lenovo Use Voice Recognition to Unlock Android Phones. https:\/\/www.techinasia.com\/baidu-lenovo-voice-recognition-android-unlock, [Accessed September, 2019]. Steven Millward. 2019. Open Sesame: Baidu Helps Lenovo Use Voice Recognition to Unlock Android Phones. https:\/\/www.techinasia.com\/baidu-lenovo-voice-recognition-android-unlock, [Accessed September, 2019]."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321705.3329842"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Parav Nagarsheth Elie Khoury Kailash Patil and Matt Garland. 2017. Replay Attack Detection Using DNN for Channel Discrimination. In INTERSPEECH.  Parav Nagarsheth Elie Khoury Kailash Patil and Matt Garland. 2017. Replay Attack Detection Using DNN for Channel Discrimination. In INTERSPEECH.","DOI":"10.21437\/Interspeech.2017-1377"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472724"},{"key":"e_1_3_2_2_43_1","volume-title":"Accessed","year":"2019","unstructured":"openstax. 2019 . Comparison of Spectrums of Voice Signals Using the L2 Norm. https:\/\/cnx.org\/contents\/gm57qegZ@1\/Comparison-of-Spectrums-of-Voice-Signals-Using-the-L2-Norm . Accessed January, 2020. openstax. 2019. Comparison of Spectrums of Voice Signals Using the L2 Norm. https:\/\/cnx.org\/contents\/gm57qegZ@1\/Comparison-of-Spectrums-of-Voice-Signals-Using-the-L2-Norm. Accessed January, 2020."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818000.2818005"},{"key":"e_1_3_2_2_45_1","volume-title":"https:\/\/portal.facebook.com\/, [accessed","author":"Portal Facebook","year":"2019","unstructured":"Facebook Portal . 2019. Facebook. https:\/\/portal.facebook.com\/, [accessed December 2019 ]. Facebook Portal. 2019. Facebook. https:\/\/portal.facebook.com\/, [accessed December 2019]."},{"key":"e_1_3_2_2_46_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Frequency_response, [accessed","author":"Response Frequency","year":"2019","unstructured":"Frequency Response . 2019. Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Frequency_response, [accessed December 2019 ]. Frequency Response. 2019. Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Frequency_response, [accessed December 2019]."},{"key":"e_1_3_2_2_47_1","volume-title":"Inaudible Voice Commands: The Long-Range Attack and Defense. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Roy Nirupam","year":"2018","unstructured":"Nirupam Roy , Sheng Shen , Haitham Hassanieh , and Romit Roy Choudhury . 2018 . Inaudible Voice Commands: The Long-Range Attack and Defense. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18) . USENIX Association, Renton, WA, 547--560. https:\/\/www.usenix.org\/conference\/nsdi18\/presentation\/roy Nirupam Roy, Sheng Shen, Haitham Hassanieh, and Romit Roy Choudhury. 2018. Inaudible Voice Commands: The Long-Range Attack and Defense. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). USENIX Association, Renton, WA, 547--560. https:\/\/www.usenix.org\/conference\/nsdi18\/presentation\/roy"},{"key":"e_1_3_2_2_48_1","unstructured":"Say-Tec. 2019. Use Say-Tec (formerly SayPay) to make payment approvals. https:\/\/www.say-tec.com\/.  Say-Tec. 2019. Use Say-Tec (formerly SayPay) to make payment approvals. https:\/\/www.say-tec.com\/."},{"key":"e_1_3_2_2_49_1","volume-title":"Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding. CoRR","author":"Lea Sch\u00f6","year":"2018","unstructured":"Lea Sch\u00f6 nherr, Katharina Kohls , Steffen Zeiler , Thorsten Holz , and Dorothea Kolossa . 2018. Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding. CoRR , Vol. abs\/ 1808 .05665 ( 2018 ). Lea Sch\u00f6 nherr, Katharina Kohls, Steffen Zeiler, Thorsten Holz, and Dorothea Kolossa. 2018. Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding. CoRR, Vol. abs\/1808.05665 (2018)."},{"key":"e_1_3_2_2_50_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Fourier_series, [accessed","author":"Wikipedia Fourier","year":"2019","unstructured":"Fourier series. 2019. Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Fourier_series, [accessed April 2019 ]. Fourier series. 2019. Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Fourier_series, [accessed April 2019]."},{"key":"e_1_3_2_2_51_1","volume-title":"Accessed","author":"Shield American Home","year":"2019","unstructured":"American Home Shield . 2019 . Top 10: Best ?Smart Home? Voice-Control Devices. https:\/\/www.ahs.com\/home-matters\/tech\/smart-home-voice-control-devices . Accessed September, 2019. American Home Shield. 2019. Top 10: Best ?Smart Home? Voice-Control Devices. https:\/\/www.ahs.com\/home-matters\/tech\/smart-home-voice-control-devices. Accessed September, 2019."},{"key":"e_1_3_2_2_52_1","volume-title":"https:\/\/www.apple.com\/siri\/, [accessed","author":"Siri Apple","year":"2019","unstructured":"Apple Siri . 2019. Apple. https:\/\/www.apple.com\/siri\/, [accessed November 2019 ]. Apple Siri. 2019. Apple. https:\/\/www.apple.com\/siri\/, [accessed November 2019]."},{"key":"e_1_3_2_2_53_1","volume-title":"Inaudible Voice Commands. CoRR","author":"Song Liwei","year":"2017","unstructured":"Liwei Song and Prateek Mittal . 2017. Inaudible Voice Commands. CoRR , Vol. abs\/ 1708 .07238 ( 2017 ). arxiv: 1708.07238 http:\/\/arxiv.org\/abs\/1708.07238 Liwei Song and Prateek Mittal. 2017. Inaudible Voice Commands. CoRR, Vol. abs\/1708.07238 (2017). arxiv: 1708.07238 http:\/\/arxiv.org\/abs\/1708.07238"},{"key":"e_1_3_2_2_54_1","volume-title":"Light Commands: Laser-Based Audio Injection on Voice-Controllable Systems. https:\/\/lightcommands.com\/20191104-Light-Commands.pdf, [accessed","author":"Sugawara Takeshi","year":"2019","unstructured":"Takeshi Sugawara , Benjamin Cyr , Sara Rampazzi , Daniel Genkin , and Kevin Fu . 2019 . Light Commands: Laser-Based Audio Injection on Voice-Controllable Systems. https:\/\/lightcommands.com\/20191104-Light-Commands.pdf, [accessed November 2019]. Takeshi Sugawara, Benjamin Cyr, Sara Rampazzi, Daniel Genkin, and Kevin Fu. 2019. Light Commands: Laser-Based Audio Injection on Voice-Controllable Systems. https:\/\/lightcommands.com\/20191104-Light-Commands.pdf, [accessed November 2019]."},{"key":"#cr-split#-e_1_3_2_2_55_1.1","doi-asserted-by":"crossref","unstructured":"Gajan Suthokumar Vidhyasaharan Sethu Chamith Wijenayake and Eliathamby Ambikairajah. 2018. Modulation Dynamic Features for the Detection of Replay Attacks. 691--695. https:\/\/doi.org\/10.21437\/Interspeech.2018--1846 10.21437\/Interspeech.2018--1846","DOI":"10.21437\/Interspeech.2018-1846"},{"key":"#cr-split#-e_1_3_2_2_55_1.2","doi-asserted-by":"crossref","unstructured":"Gajan Suthokumar Vidhyasaharan Sethu Chamith Wijenayake and Eliathamby Ambikairajah. 2018. Modulation Dynamic Features for the Detection of Replay Attacks. 691--695. https:\/\/doi.org\/10.21437\/Interspeech.2018--1846","DOI":"10.21437\/Interspeech.2018-1846"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"e_1_3_2_2_57_1","volume-title":"http:\/\/wiki.seeedstudio.com\/ReSpeaker_Core_v2.0\/, [accessed","author":"Seeed Studio ReSpeaker","year":"2019","unstructured":"ReSpeaker Core v2.0. 2019. Seeed Studio . http:\/\/wiki.seeedstudio.com\/ReSpeaker_Core_v2.0\/, [accessed December 2019 ]. ReSpeaker Core v2.0. 2019. Seeed Studio. http:\/\/wiki.seeedstudio.com\/ReSpeaker_Core_v2.0\/, [accessed December 2019]."},{"key":"e_1_3_2_2_58_1","volume-title":"9th USENIX Workshop on Offensive Technologies (WOOT 15)","author":"Vaidya Tavish","year":"2015","unstructured":"Tavish Vaidya , Yuankai Zhang , Micah Sherr , and Clay Shields . 2015 . Cocaine Noodles: Exploiting the Gap between Human and Machine Speech Recognition . In 9th USENIX Workshop on Offensive Technologies (WOOT 15) . USENIX Association, Washington, D.C. https:\/\/www.usenix.org\/conference\/woot15\/workshop-program\/presentation\/vaidya Tavish Vaidya, Yuankai Zhang, Micah Sherr, and Clay Shields. 2015. Cocaine Noodles: Exploiting the Gap between Human and Machine Speech Recognition. In 9th USENIX Workshop on Offensive Technologies (WOOT 15). USENIX Association, Washington, D.C. https:\/\/www.usenix.org\/conference\/woot15\/workshop-program\/presentation\/vaidya"},{"key":"e_1_3_2_2_59_1","volume-title":"Detecting Replay Attacks from Far-Field Recordings on Speaker Verification Systems","author":"Villalba Jes\u00fas","unstructured":"Jes\u00fas Villalba and Eduardo Lleida . 2011a. Detecting Replay Attacks from Far-Field Recordings on Speaker Verification Systems . In Biometrics and ID Management, Claus Vielhauer, Jana Dittmann, Andrzej Drygajlo, Niels Christian Juul, and Michael C. Fairhurst (Eds.). Springer Berlin Heidelberg , Berlin, Heidelberg , 274--285. Jes\u00fas Villalba and Eduardo Lleida. 2011a. Detecting Replay Attacks from Far-Field Recordings on Speaker Verification Systems. In Biometrics and ID Management, Claus Vielhauer, Jana Dittmann, Andrzej Drygajlo, Niels Christian Juul, and Michael C. Fairhurst (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 274--285."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCST.2011.6095943"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"crossref","unstructured":"Xin Wang Junichi Yamagishi Massimiliano Todisco Hector Delgado Andreas Nautsch Nicholas Evans Md Sahidullah Ville Vestman Tomi Kinnunen Kong Aik Lee Lauri Juvela Paavo Alku Yu-Huai Peng Hsin-Te Hwang Yu Tsao Hsin-Min Wang Sebastien Le Maguer Markus Becker Fergus Henderson Rob Clark Yu Zhang Quan Wang Ye Jia Kai Onuma Koji Mushika Takashi Kaneda Yuan Jiang Li-Juan Liu Yi-Chiao Wu Wen-Chin Huang Tomoki Toda Kou Tanaka Hirokazu Kameoka Ingmar Steiner Driss Matrouf Jean-Francois Bonastre Avashna Govender Srikanth Ronanki Jing-Xuan Zhang and Zhen-Hua Ling. 2019. ASVspoof 2019: a large-scale public database of synthetic converted and replayed speech. arxiv: 1911.01601 [eess.AS]  Xin Wang Junichi Yamagishi Massimiliano Todisco Hector Delgado Andreas Nautsch Nicholas Evans Md Sahidullah Ville Vestman Tomi Kinnunen Kong Aik Lee Lauri Juvela Paavo Alku Yu-Huai Peng Hsin-Te Hwang Yu Tsao Hsin-Min Wang Sebastien Le Maguer Markus Becker Fergus Henderson Rob Clark Yu Zhang Quan Wang Ye Jia Kai Onuma Koji Mushika Takashi Kaneda Yuan Jiang Li-Juan Liu Yi-Chiao Wu Wen-Chin Huang Tomoki Toda Kou Tanaka Hirokazu Kameoka Ingmar Steiner Driss Matrouf Jean-Francois Bonastre Avashna Govender Srikanth Ronanki Jing-Xuan Zhang and Zhen-Hua Ling. 2019. ASVspoof 2019: a large-scale public database of synthetic converted and replayed speech. arxiv: 1911.01601 [eess.AS]","DOI":"10.1016\/j.csl.2020.101114"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2011.6016982"},{"key":"e_1_3_2_2_63_1","volume-title":"Accessed","year":"2019","unstructured":"Wikipedia. 2019 . Ringing artifacts. https:\/\/en.wikipedia.org\/wiki\/Ringing_artifacts . Accessed September, 2019. Wikipedia. 2019. Ringing artifacts. https:\/\/en.wikipedia.org\/wiki\/Ringing_artifacts. Accessed September, 2019."},{"key":"e_1_3_2_2_64_1","volume-title":"Accessed","year":"2020","unstructured":"Wikipedia. 2020 . Wavelet packet decomposition. https:\/\/en.wikipedia.org\/wiki\/Wavelet_packet_decomposition . Accessed April, 2020. Wikipedia. 2020. Wavelet packet decomposition. https:\/\/en.wikipedia.org\/wiki\/Wavelet_packet_decomposition. Accessed April, 2020."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-776"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"e_1_3_2_2_67_1","volume-title":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. 1--9. https:\/\/doi.org\/10","author":"Wu Z.","year":"2013","unstructured":"Z. Wu and H. Li . 2013. Voice conversion and spoofing attack on speaker verification systems . In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. 1--9. https:\/\/doi.org\/10 .1109\/APSIPA. 2013 .6694344 10.1109\/APSIPA.2013.6694344 Z. Wu and H. Li. 2013. Voice conversion and spoofing attack on speaker verification systems. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. 1--9. https:\/\/doi.org\/10.1109\/APSIPA.2013.6694344"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1229\/1\/012079"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3354248"},{"key":"e_1_3_2_2_70_1","volume-title":"CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition. In 27th USENIX Security Symposium (USENIX Security 18)","author":"Yuan Xuejing","unstructured":"Xuejing Yuan , Yuxuan Chen , Yue Zhao , Yunhui Long , Xiaokang Liu , Kai Chen , Shengzhi Zhang , Heqing Huang , XiaoFeng Wang , and Carl A. Gunter . 2018 . CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition. In 27th USENIX Security Symposium (USENIX Security 18) . USENIX Association, Baltimore, MD, 49--64. https:\/\/www.usenix.org\/conference\/usenixsecurity18\/presentation\/yuan-xuejing Xuejing Yuan, Yuxuan Chen, Yue Zhao, Yunhui Long, Xiaokang Liu, Kai Chen, Shengzhi Zhang, Heqing Huang, XiaoFeng Wang, and Carl A. Gunter. 2018. CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition. In 27th USENIX Security Symposium (USENIX Security 18). USENIX Association, Baltimore, MD, 49--64. https:\/\/www.usenix.org\/conference\/usenixsecurity18\/presentation\/yuan-xuejing"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134052"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133962"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978296"},{"key":"e_1_3_2_2_74_1","volume-title":"2019 b. Dangerous Skills: Understanding and Mitigating Security Risks of Voice-Controlled Third-Party Functions on Virtual Personal Assistant Systems","author":"Zhang Nan","year":"2019","unstructured":"Nan Zhang , Xianghang Mi , Xuan Feng , XiaoFeng Wang , Yuan Tian , and Feng Qian . 2019 b. Dangerous Skills: Understanding and Mitigating Security Risks of Voice-Controlled Third-Party Functions on Virtual Personal Assistant Systems . In IEEE S &P 2019 . Nan Zhang, Xianghang Mi, Xuan Feng, XiaoFeng Wang, Yuan Tian, and Feng Qian. 2019 b. Dangerous Skills: Understanding and Mitigating Security Risks of Voice-Controlled Third-Party Functions on Virtual Personal Assistant Systems. In IEEE S&P 2019."},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23525"},{"key":"#cr-split#-e_1_3_2_2_76_1.1","doi-asserted-by":"crossref","unstructured":"M. Zhou Z. Qin X. Lin S. Hu Q. Wang and K. Ren. 2019. Hidden Voice Commands: Attacks and Defenses on the VCS of Autonomous Driving Cars. IEEE Wireless Communications (2019) 1--6. https:\/\/doi.org\/10.1109\/MWC.2019.1800477 10.1109\/MWC.2019.1800477","DOI":"10.1109\/MWC.2019.1800477"},{"key":"#cr-split#-e_1_3_2_2_76_1.2","doi-asserted-by":"crossref","unstructured":"M. Zhou Z. Qin X. Lin S. Hu Q. Wang and K. Ren. 2019. Hidden Voice Commands: Attacks and Defenses on the VCS of Autonomous Driving Cars. IEEE Wireless Communications (2019) 1--6. https:\/\/doi.org\/10.1109\/MWC.2019.1800477","DOI":"10.1109\/MWC.2019.1800477"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2010.0348"}],"event":{"name":"CCS '20: 2020 ACM SIGSAC Conference on Computer and Communications Security","location":"Virtual Event USA","acronym":"CCS '20","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3372297.3417254","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3372297.3417254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:30Z","timestamp":1750197690000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3372297.3417254"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,30]]},"references-count":80,"alternative-id":["10.1145\/3372297.3417254","10.1145\/3372297"],"URL":"https:\/\/doi.org\/10.1145\/3372297.3417254","relation":{},"subject":[],"published":{"date-parts":[[2020,10,30]]},"assertion":[{"value":"2020-11-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}