{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:19:54Z","timestamp":1783009194770,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"IIS","award":["2311596, 2311597"],"award-info":[{"award-number":["2311596, 2311597"]}]},{"name":"OAC","award":["2139358"],"award-info":[{"award-number":["2139358"]}]},{"name":"CNS","award":["2114220, 2120276, 2145389, 2201465, 2154507"],"award-info":[{"award-number":["2114220, 2120276, 2145389, 2201465, 2154507"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1145\/3658644.3670358","type":"proceedings-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T12:19:20Z","timestamp":1733746760000},"page":"153-167","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["SAFARI: Speech-Associated Facial Authentication for AR\/VR Settings via Robust VIbration Signatures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2084-6383","authenticated-orcid":false,"given":"Tianfang","family":"Zhang","sequence":"first","affiliation":[{"name":"Rutgers University, New Brunswick, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5523-8647","authenticated-orcid":false,"given":"Qiufan","family":"Ji","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology, Newark, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5528-0783","authenticated-orcid":false,"given":"Zhengkun","family":"Ye","sequence":"additional","affiliation":[{"name":"Temple University, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2874-316X","authenticated-orcid":false,"given":"Md Mojibur Rahman Redoy","family":"Akanda","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4136-7004","authenticated-orcid":false,"given":"Ahmed Tanvir","family":"Mahdad","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7599-202X","authenticated-orcid":false,"given":"Cong","family":"Shi","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology, Newark, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3984-6973","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Temple University, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6083-104X","authenticated-orcid":false,"given":"Nitesh","family":"Saxena","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3994-766X","authenticated-orcid":false,"given":"Yingying","family":"Chen","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. Apple Vision Pro. https:\/\/www.apple.com\/apple-vision-pro\/. (2023)."},{"key":"e_1_3_2_1_2_1","unstructured":"2023. Meta Quest 3. https:\/\/www.meta.com\/quest\/quest-3\/. (2023)."},{"key":"e_1_3_2_1_3_1","unstructured":"2023. Microsoft HoloLens 2. https:\/\/www.microsoft.com\/en-us\/hololens\/. (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414263"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of IEEE Symposium on Security and Privacy (SP). 1000--1017","author":"Anand S. A.","unstructured":"S. A. Anand and N. Saxena. 2018. Speechless: Analyzing the Threat to Speech Privacy from Smartphone Motion Sensors. In Proceedings of IEEE Symposium on Security and Privacy (SP). 1000--1017."},{"key":"e_1_3_2_1_6_1","volume-title":"Spearphone: A speech privacy exploit via accelerometer-sensed reverberations from smartphone loudspeakers. arXiv preprint arXiv:1907.05972","author":"Anand S Abhishek","year":"2019","unstructured":"S Abhishek Anand, Chen Wang, Jian Liu, Nitesh Saxena, and Yingying Chen. 2019. Spearphone: A speech privacy exploit via accelerometer-sensed reverberations from smartphone loudspeakers. arXiv preprint arXiv:1907.05972 (2019)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2020.24076"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.07.001"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1455770.1455804"},{"key":"e_1_3_2_1_10_1","volume-title":"Detecting Audio DeepFakes Through Vocal Tract Reconstruction. In USENIX Security Symposium. https:\/\/api.semanticscholar.org\/CorpusID:249059207","author":"Blue Logan","year":"2022","unstructured":"Logan Blue, Kevin Warren, Hadi Abdullah, Cassidy Gibson, Luis Vargas, J. O'Dell, Kevin R. B. Butler, and Patrick Traynor. 2022. Who Are You (I Really Wanna Know)? Detecting Audio DeepFakes Through Vocal Tract Reconstruction. In USENIX Security Symposium. https:\/\/api.semanticscholar.org\/CorpusID:249059207"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Pattern Recognition Applications and Methods","volume":"2","author":"Cappelletta Luca","year":"2012","unstructured":"Luca Cappelletta and Naomi Harte. 2012. Phoneme-to-viseme mapping for visual speech recognition. In International Conference on Pattern Recognition Applications and Methods, Vol. 2. SCITEPRESS, 322--329."},{"key":"e_1_3_2_1_12_1","volume-title":"Hidden Voice Commands. In USENIX Security Symposium. 513--530","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 USENIX Security Symposium. 513--530."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-39555-5_35"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.133"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450494"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/508171.508174"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3117811.3117823"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Ceenu George M. Khamis Emanuel von Zezschwitz Marinus Burger Henri Schmidt Florian Alt and Heinrich Hussmann. 2017. Seamless and Secure VR: Adapting and Evaluating Established Authentication Systems for Virtual Reality. https:\/\/api.semanticscholar.org\/CorpusID:6671814","DOI":"10.14722\/usec.2017.23028"},{"key":"e_1_3_2_1_20_1","volume-title":"Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong, Yu-An Chung, and James Glass. 2021. Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778 (2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Coarticulation and speech impairment. The handbook of clinical linguistics","author":"Hardcastle Bill","year":"2008","unstructured":"Bill Hardcastle and Kris Tjaden. 2008. Coarticulation and speech impairment. The handbook of clinical linguistics (2008), 506--524."},{"key":"e_1_3_2_1_22_1","volume-title":"I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry. In Interspeech. Citeseer, 930--934","author":"Hautam\u00e4ki Rosa Gonz\u00e1lez","year":"2013","unstructured":"Rosa Gonz\u00e1lez Hautam\u00e4ki, Tomi Kinnunen, Ville Hautam\u00e4ki, Timo Leino, and Anne-Maria Laukkanen. 2013. I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry. In Interspeech. Citeseer, 930--934."},{"key":"e_1_3_2_1_23_1","volume-title":"Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), 770--778. https:\/\/api.semanticscholar.org\/CorpusID:206594692"},{"key":"e_1_3_2_1_24_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858436"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Tomi Kinnunen Md Sahidullah H\u00e9ctor Delgado Massimiliano Todisco Nicholas Evans Junichi Yamagishi and Kong Aik Lee. 2017. The ASVspoof 2017 challenge: Assessing the limits of replay spoofing attack detection. (2017).","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.69"},{"key":"e_1_3_2_1_29_1","volume-title":"Using penalized contrasts for the change-point problem. Signal processing 85, 8","author":"Lavielle Marc","year":"2005","unstructured":"Marc Lavielle. 2005. Using penalized contrasts for the change-point problem. Signal processing 85, 8 (2005), 1501--1510."},{"key":"e_1_3_2_1_30_1","volume-title":"Audio-to-Visual Conversion Using Hidden Markov Models. In Pacific Rim International Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:32064363","author":"Lee Soonkyu","year":"2002","unstructured":"Soonkyu Lee and Dongsuk Yook. 2002. Audio-to-Visual Conversion Using Hidden Markov Models. In Pacific Rim International Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:32064363"},{"key":"e_1_3_2_1_31_1","volume-title":"VibHead: An Authentication Scheme for Smart Headsets through Vibration. arXiv preprint arXiv:2306.17002","author":"Li Feng","year":"2023","unstructured":"Feng Li, Jiayi Zhao, Huan Yang, Dongxiao Yu, Yuanfeng Zhou, and Yiran Shen. 2023. VibHead: An Authentication Scheme for Smart Headsets through Vibration. arXiv preprint arXiv:2306.17002 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Knowledge-driven Biometric Authentication in Virtual Reality. Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems","author":"Mathis Florian","year":"2020","unstructured":"Florian Mathis, Hassan Ismail Fawaz, and M. Khamis. 2020. Knowledge-driven Biometric Authentication in Virtual Reality. Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems (2020). https:\/\/api.semanticscholar.org\/CorpusID:212997365"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209582.3209591"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of USENIX Security Symposium. 1053--1067","author":"Michalevsky Yan","year":"2014","unstructured":"Yan Michalevsky, Dan Boneh, and Gabi Nakibly. 2014. Gyrophone: Recognizing Speech from Gyroscope Signals. In Proceedings of USENIX Security Symposium. 1053--1067."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469029"},{"key":"e_1_3_2_1_36_1","unstructured":"Oculus. 2023. Oculus PC SDK v23. (2023). https:\/\/developer.oculus.com\/downloads\/ package\/oculus-sdk-for-windows\/."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20102944"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385378.3385385"},{"key":"e_1_3_2_1_39_1","volume-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv abs\/1505.04597","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv abs\/1505.04597 (2015). https:\/\/api.semanticscholar.org\/CorpusID:3719281"},{"key":"e_1_3_2_1_40_1","volume-title":"Archisound: Audio generation with diffusion. arXiv preprint arXiv:2301.13267","author":"Schneider Flavio","year":"2023","unstructured":"Flavio Schneider. 2023. Archisound: Audio generation with diffusion. arXiv preprint arXiv:2301.13267 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427228.3427259"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483272"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"David Snyder Daniel Garcia-Romero Daniel Povey and Sanjeev Khudanpur. 2017. Deep Neural Network Embeddings for Text-Independent Speaker Verification. In Interspeech. 999--1003.","DOI":"10.21437\/Interspeech.2017-620"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"e_1_3_2_1_47_1","volume-title":"The future of ophthalmology and vision science with the Apple Vision Pro. Eye","author":"Waisberg Ethan","year":"2023","unstructured":"Ethan Waisberg, Joshua Ong, Mouayad Masalkhi, Nasif Zaman, Prithul Sarker, Andrew G Lee, and Alireza Tavakkoli. 2023. The future of ophthalmology and vision science with the Apple Vision Pro. Eye (2023), 1--2."},{"key":"e_1_3_2_1_48_1","volume-title":"Low-effort VR Headset User Authentication Using Head-reverberated Sounds with Replay Resistance. 2023 IEEE Symposium on Security and Privacy (SP)","author":"Wang Ruxin","year":"2023","unstructured":"Ruxin Wang, Long Huang, and Chen Wang. 2023. Low-effort VR Headset User Authentication Using Head-reverberated Sounds with Replay Resistance. 2023 IEEE Symposium on Security and Privacy (SP) (2023), 3450--3465. https:\/\/api.semanticscholar.org\/CorpusID:260003730"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451769"},{"key":"e_1_3_2_1_50_1","volume-title":"et al","author":"Wang Yuxuan","year":"2017","unstructured":"Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, et al . 2017. Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)."},{"key":"e_1_3_2_1_51_1","volume-title":"https:\/\/en.wikipedia.org\/wiki\/Topographic_prominence","author":"Prominence Topographic","year":"2023","unstructured":"Wikipedia. 2023. Topographic Prominence. (2023). https:\/\/en.wikipedia.org\/wiki\/Topographic_prominence."},{"key":"e_1_3_2_1_52_1","unstructured":"Tong Wu Zhihao Fan Xiao Liu Yeyun Gong Yelong Shen Jian Jiao Hai-Tao Zheng Juntao Li Zhongyu Wei Jian Guo et al. 2023. AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation. arXiv preprint arXiv:2305.09515 (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"Design and Analysis of Shoulder Surfing Resistant PIN Based Authentication Mechanisms on Google Glass. In Financial Cryptography Workshops. https:\/\/api.semanticscholar.org\/CorpusID:16027399","author":"Yadav Dhruv Kumar","unstructured":"Dhruv Kumar Yadav, Beatrice Ionascu, Sai Vamsi Krishna Ongole, Aditi Roy, and Nasir D. Memon. 2015. Design and Analysis of Shoulder Surfing Resistant PIN Based Authentication Mechanisms on Google Glass. In Financial Cryptography Workshops. https:\/\/api.semanticscholar.org\/CorpusID:16027399"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3354248"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524542"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2742647.2742658"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133962"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978296"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3244502"}],"event":{"name":"CCS '24: ACM SIGSAC Conference on Computer and Communications Security","location":"Salt Lake City UT USA","acronym":"CCS '24","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658644.3670358","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658644.3670358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:52:28Z","timestamp":1755841948000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658644.3670358"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":60,"alternative-id":["10.1145\/3658644.3670358","10.1145\/3658644"],"URL":"https:\/\/doi.org\/10.1145\/3658644.3670358","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2024-12-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}