{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:37:48Z","timestamp":1780418268346,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,19]],"date-time":"2023-11-19T00:00:00Z","timestamp":1700352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1805400"],"award-info":[{"award-number":["2020YFB1805400"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024ZCJH05"],"award-info":[{"award-number":["2024ZCJH05"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,19]]},"DOI":"10.1145\/3689217.3690615","type":"proceedings-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:22:01Z","timestamp":1732040521000},"page":"13-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Mitigating Unauthorized Speech Synthesis for Voice Protection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0066-8214","authenticated-orcid":false,"given":"Zhisheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6293-5121","authenticated-orcid":false,"given":"Qianyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1388-7715","authenticated-orcid":false,"given":"Derui","family":"Wang","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7461-9670","authenticated-orcid":false,"given":"Pengyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5766-0846","authenticated-orcid":false,"given":"Yuxin","family":"Cao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2177-5531","authenticated-orcid":false,"given":"Kai","family":"Ye","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2032-665X","authenticated-orcid":false,"given":"Jie","family":"Hao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Machine Learning. PMLR, 284--293","author":"Athalye Anish","year":"2018","unstructured":"Anish Athalye, Logan Engstrom, Andrew Ilyas, and Kevin Kwok. 2018. Synthesizing robust adversarial examples. In International Conference on Machine Learning. PMLR, 284--293."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"e_1_3_2_1_5_1","volume-title":"Detecting Audio DeepFakes Through Vocal Tract Reconstruction. In 31st USENIX Security Symposium (USENIX Security 22)","author":"Blue Logan","year":"2022","unstructured":"Logan Blue, Kevin Warren, Hadi Abdullah, Cassidy Gibson, Luis Vargas, Jessica O'Dell, Kevin Butler, and Patrick Traynor. 2022. Who Are You (I Really Wanna Know)? Detecting Audio DeepFakes Through Vocal Tract Reconstruction. In 31st USENIX Security Symposium (USENIX Security 22). 2691--2708."},{"key":"e_1_3_2_1_6_1","volume-title":"Dp-instahide: Provably defusing poisoning and backdoor attacks with differentially private data augmentations. arXiv preprint arXiv:2103.02079","author":"Borgnia Eitan","year":"2021","unstructured":"Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, and Tom Goldstein. 2021. Dp-instahide: Provably defusing poisoning and backdoor attacks with differentially private data augmentations. arXiv preprint arXiv:2103.02079 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning. PMLR, 2709--2720","author":"Casanova Edresson","year":"2022","unstructured":"Edresson Casanova, Julian Weber, Christopher D Shulby, Arnaldo Candido Junior, Eren G\u00f6lge, and Moacir A Ponti. 2022. Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone. In International Conference on Machine Learning. PMLR, 2709--2720."},{"key":"e_1_3_2_1_8_1","volume-title":"Adaspeech: Adaptive text to speech for custom voice. arXiv preprint arXiv:2103.00993","author":"Chen Mingjian","year":"2021","unstructured":"Mingjian Chen, Xu Tan, Bohan Li, Yanqing Liu, Tao Qin, Sheng Zhao, and Tie-Yan Liu. 2021. Adaspeech: Adaptive text to speech for custom voice. arXiv preprint arXiv:2103.00993 (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747186"},{"key":"e_1_3_2_1_10_1","volume-title":"Naturalness-& Timbre-Preserving Real-Time Voice Anonymization. In 32nd USENIX Security Symposium (USENIX Security 23)","author":"Deng Jiangyi","year":"2023","unstructured":"Jiangyi Deng, Fei Teng, Yanjiao Chen, Xiaofu Chen, Zhaohui Wang, and Wenyuan Xu. 2023. V-Cloak: Intelligibility-, Naturalness-& Timbre-Preserving Real-Time Voice Anonymization. In 32nd USENIX Security Symposium (USENIX Security 23). 5181--5198."},{"key":"e_1_3_2_1_11_1","first-page":"3830","article-title":"ECAPA-TDNN","volume":"2020","author":"Desplanques Brecht","year":"2020","unstructured":"Brecht Desplanques, Jenthe Thienpondt, and Kris Demuynck. 2020. ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification. In Proc. Interspeech 2020. 3830--3834.","journal-title":"In Proc. Interspeech"},{"key":"e_1_3_2_1_12_1","unstructured":"Yuchen Fan Yao Qian Feng-Long Xie and Frank K Soong. 2014. TTS synthesis with bidirectional LSTM based recurrent neural networks. In Fifteenth annual conference of the international speech communication association."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-28"},{"key":"e_1_3_2_1_14_1","volume-title":"Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning. In International Conference on Learning Representations (ICLR).","author":"Fu Shaopeng","year":"2022","unstructured":"Shaopeng Fu, Fengxiang He, Yang Liu, Li Shen, and Dacheng Tao. 2022. Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_15_1","volume-title":"PosCUDA: Position based Convolution for Unlearnable Audio Datasets. arXiv preprint arXiv:2401.02135","author":"Gokul Vignesh","year":"2024","unstructured":"Vignesh Gokul and Shlomo Dubnov. 2024. PosCUDA: Position based Convolution for Unlearnable Audio Datasets. arXiv preprint arXiv:2401.02135 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3231480"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102875"},{"key":"e_1_3_2_1_18_1","volume-title":"2021 IEEE Spoken Language Technology Workshop (SLT). IEEE, 552--559","author":"Lin Yist Y","year":"2021","unstructured":"Chien-yu Huang, Yist Y Lin, Hung-yi Lee, and Lin-shan Lee. 2021. Defending your voice: Adversarial attack on voice conversion. In 2021 IEEE Spoken Language Technology Workshop (SLT). IEEE, 552--559."},{"key":"e_1_3_2_1_19_1","volume-title":"Unlearnable Examples: Making Personal Data Unexploitable. In International Conference on Learning Representations (ICLR).","author":"Huang Hanxun","year":"2021","unstructured":"Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey, and Yisen Wang. 2021. Unlearnable Examples: Making Personal Data Unexploitable. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_20_1","unstructured":"Keith Ito and Linda Johnson. 2017. The LJ Speech Dataset. https:\/\/keithito.com\/LJ-Speech-Dataset\/."},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Learning Representations (ILCR).","author":"Jiang Ziyue","year":"2024","unstructured":"Ziyue Jiang, Jinglin Liu, Yi Ren, Jinzheng He, Zhenhui Ye, Shengpeng Ji, Qian Yang, Chen Zhang, Pengfei Wei, Chunfeng Wang, Xiang Yin, Zejun MA, and Zhou Zhao. 2024. Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis. In International Conference on Learning Representations (ILCR)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095296"},{"key":"e_1_3_2_1_23_1","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim Jaehyeon","year":"2020","unstructured":"Jaehyeon Kim, Sungwon Kim, Jungil Kong, and Sungroh Yoon. 2020. Glow-tts: A generative flow for text-to-speech via monotonic alignment search. Advances in Neural Information Processing Systems, Vol. 33 (2020), 8067--8077.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Machine Learning. PMLR, 5530--5540","author":"Kim Jaehyeon","year":"2021","unstructured":"Jaehyeon Kim, Jungil Kong, and Juhee Son. 2021. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In International Conference on Machine Learning. PMLR, 5530--5540."},{"key":"e_1_3_2_1_25_1","volume-title":"Carnegie Mellon University ARCTIC databases for speech synthesis","author":"Kominek John","year":"2003","unstructured":"John Kominek. 2003. Carnegie Mellon University ARCTIC databases for speech synthesis. Carnegie Mellon University-LTI (2003)."},{"key":"e_1_3_2_1_26_1","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong Jungil","year":"2020","unstructured":"Jungil Kong, Jaehyeon Kim, and Jaekyoung Bae. 2020. Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis. Advances in Neural Information Processing Systems, Vol. 33 (2020), 17022--17033.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","volume-title":"Lucas Gestin, Wei Zhen Teoh, Jose Sotelo, Alexandre De Brebisson, Yoshua Bengio, and Aaron C Courville.","author":"Kumar Kundan","year":"2019","unstructured":"Kundan Kumar, Rithesh Kumar, Thibault De Boissiere, Lucas Gestin, Wei Zhen Teoh, Jose Sotelo, Alexandre De Brebisson, Yoshua Bengio, and Aaron C Courville. 2019. Melgan: Generative adversarial networks for conditional waveform synthesis. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_28_1","volume-title":"Voice Guard: Protecting Voice Privacy with Strong and Imperceptible Adversarial Perturbation in the Time Domain.. In IJCAI. 4812--4820.","author":"Li Jingyang","year":"2023","unstructured":"Jingyang Li, Dengpan Ye, Long Tang, Chuanxi Chen, and Shengshan Hu. 2023. Voice Guard: Protecting Voice Privacy with Strong and Imperceptible Adversarial Perturbation in the Time Domain.. In IJCAI. 4812--4820."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627106.3627183"},{"key":"e_1_3_2_1_31_1","volume-title":"International conference on machine learning. PMLR, 22473--22487","author":"Liu Zhuoran","year":"2023","unstructured":"Zhuoran Liu, Zhengyu Zhao, and Martha Larson. 2023. Image shortcut squeezing: Countering perturbative availability poisons with compression. In International conference on machine learning. PMLR, 22473--22487."},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS55849.2022.9975428"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning. PMLR, 28492--28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning. PMLR, 28492--28518."},{"key":"e_1_3_2_1_40_1","volume-title":"International Conference on Learning Representations.","author":"Ren Yi","year":"2021","unstructured":"Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2021. FastSpeech 2: Fast and High-Quality End-to-End Text to Speech. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Tim Sainburg. 2019. timsainb\/noisereduce: v1.0. https:\/\/doi.org\/10.5281\/zenodo.3243139","DOI":"10.5281\/zenodo.3243139"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"e_1_3_2_1_44_1","volume-title":"Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE transactions on medical imaging","author":"Tajbakhsh Nima","year":"2016","unstructured":"Nima Tajbakhsh, Jae Y Shin, Suryakanth R Gurudu, R Todd Hurst, Christopher B Kendall, Michael B Gotway, and Jianming Liang. 2016. Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE transactions on medical imaging, Vol. 35, 5 (2016), 1299--1312."},{"key":"e_1_3_2_1_45_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3558482.3590189"},{"key":"e_1_3_2_1_47_1","volume-title":"Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135","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_48_1","volume-title":"International Conference on Machine Learning. PMLR, 25154--25165","author":"Yang Yu","year":"2022","unstructured":"Yu Yang, Tian Yu Liu, and Baharan Mirzasoleiman. 2022. Not all poisons are created equal: Robust training against data poisoning. In International Conference on Machine Learning. PMLR, 25154--25165."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3407600"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3035416"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-596"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623209"},{"key":"e_1_3_2_1_53_1","volume-title":"Libritts: A corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882","author":"Zen Heiga","year":"2019","unstructured":"Heiga Zen, Viet Dang, Rob Clark, Yu Zhang, Ron J Weiss, Ye Jia, Zhifeng Chen, and Yonghui Wu. 2019. Libritts: A corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882 (2019)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"e_1_3_2_1_55_1","volume-title":"Statistical parametric speech synthesis using deep neural networks. In 2013 ieee international conference on acoustics, speech and signal processing","author":"Zen Heiga","unstructured":"Heiga Zen, Andrew Senior, and Mike Schuster. 2013. Statistical parametric speech synthesis using deep neural networks. In 2013 ieee international conference on acoustics, speech and signal processing. IEEE, 7962--7966."},{"key":"e_1_3_2_1_56_1","volume-title":"Statistical parametric speech synthesis. speech communication","author":"Zen Heiga","year":"2009","unstructured":"Heiga Zen, Keiichi Tokuda, and Alan W Black. 2009. Statistical parametric speech synthesis. speech communication, Vol. 51, 11 (2009), 1039--1064."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3100641"}],"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 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689217.3690615","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689217.3690615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:12:49Z","timestamp":1755972769000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689217.3690615"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,19]]},"references-count":57,"alternative-id":["10.1145\/3689217.3690615","10.1145\/3689217"],"URL":"https:\/\/doi.org\/10.1145\/3689217.3690615","relation":{},"subject":[],"published":{"date-parts":[[2023,11,19]]},"assertion":[{"value":"2024-11-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}