{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:30:00Z","timestamp":1774539000746,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Gansu Province Key Research and Development Plan - Industrial Project","award":["22YF7GA004"],"award-info":[{"award-number":["22YF7GA004"]}]},{"name":"Gansu Province Science and Technology Major Project - Industrial Project","award":["22ZD6GA048"],"award-info":[{"award-number":["22ZD6GA048"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613841","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"8552-8560","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["SiFDetectCracker: An Adversarial Attack Against Fake Voice Detection Based on Speaker-Irrelative Features"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0695-2187","authenticated-orcid":false,"given":"Xuan","family":"Hai","sequence":"first","affiliation":[{"name":"Lanzhou University, Lanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3685-4852","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Lanzhou University, Lanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3260-6771","authenticated-orcid":false,"given":"Yuan","family":"Tan","sequence":"additional","affiliation":[{"name":"Lanzhou University, Lanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8054-5446","authenticated-orcid":false,"given":"Qingguo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Lanzhou University, Lanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Deep residual neural networks for audio spoofing detection. arXiv preprint arXiv:1907.00501","author":"Alzantot Moustafa","year":"2019","unstructured":"Moustafa Alzantot, ZiqiWang, and Mani B Srivastava. 2019. Deep residual neural networks for audio spoofing detection. arXiv preprint arXiv:1907.00501 (2019)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115465"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3033291"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-4"},{"key":"e_1_3_2_1_7_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_1_8_1","volume-title":"Jun Wang, Dan Su, Dong Yu, Yi Ren, and Zhou Zhao.","author":"Huang Rongjie","year":"2022","unstructured":"Rongjie Huang, Max WY Lam, Jun Wang, Dan Su, Dong Yu, Yi Ren, and Zhou Zhao. 2022. Fastdiff: A fast conditional diffusion model for high-quality speech synthesis. arXiv preprint arXiv:2204.09934 (2022)."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR, 2137--2146","author":"Ilyas Andrew","year":"2018","unstructured":"Andrew Ilyas, Logan Engstrom, Anish Athalye, and Jessy Lin. 2018. Blackbox adversarial attacks with limited queries and information. In International Conference on Machine Learning. PMLR, 2137--2146."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116770"},{"key":"e_1_3_2_1_11_1","unstructured":"The Wall Street Journal. 2019. Fraudsters Used AI to Mimic CEO's Voice in Unusual Cybercrime Case. https:\/\/www.wsj.com\/articles\/fraudsters-use-ai-tomimicceos-voice-in-unusual-cybercrime-case-11567157402 ."},{"key":"e_1_3_2_1_12_1","volume-title":"Diffwave: A versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761","author":"Kong Zhifeng","year":"2020","unstructured":"Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, and Bryan Catanzaro. 2020. Diffwave: A versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"BDDM: Bilateral denoising diffusion models for fast and high-quality speech synthesis. arXiv preprint arXiv:2203.13508","author":"Lam WY","year":"2022","unstructured":"MaxWY Lam, JunWang, Dan Su, and Dong Yu. 2022. BDDM: Bilateral denoising diffusion models for fast and high-quality speech synthesis. arXiv preprint arXiv:2203.13508 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR, 3866--3876","author":"Li Yandong","year":"2019","unstructured":"Yandong Li, Lijun Li, LiqiangWang, Tong Zhang, and Boqing Gong. 2019. Nattack: Learning the distributions of adversarial examples for an improved black-box attack on deep neural networks. In International Conference on Machine Learning. PMLR, 3866--3876."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Xin Liu Xiaokang Zhou and Qingguo Zhou. 2022. Human or Not: Can You Really Detect the Fake Voices? https:\/\/doi.org\/10.13140\/RG.2.2.19572.83849","DOI":"10.13140\/RG.2.2.19572.83849"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101096"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"e_1_3_2_1_18_1","volume-title":"Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499","author":"van den Oord Aaron","year":"2016","unstructured":"Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. 2016. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR51284.2021.00076"},{"key":"e_1_3_2_1_20_1","volume-title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis. arXiv preprint arXiv:2203.16930","author":"Siuzdak Hubert","year":"2022","unstructured":"Hubert Siuzdak, Piotr Dura, Pol van Rijn, and Nori Jacoby. 2022. WavThruVec: Latent speech representation as intermediate features for neural speech synthesis. arXiv preprint arXiv:2203.16930 (2022)."},{"key":"e_1_3_2_1_21_1","volume-title":"Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199","author":"Szegedy Christian","year":"2013","unstructured":"Christian Szegedy,Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"e_1_3_2_1_24_1","volume-title":"Text-to-speech synthesis","author":"Taylor Paul","unstructured":"Paul Taylor. 2009. Text-to-speech synthesis. Cambridge university press."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-41"},{"key":"e_1_3_2_1_26_1","unstructured":"K Tokuda. 2010. The HMM-based speech synthesis system (HTS). http:\/\/hts. sp. nitech. ac. jp\/ (2010)."},{"key":"e_1_3_2_1_27_1","volume-title":"Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis. arXiv preprint arXiv:2005.05957","author":"Valle Rafael","year":"2020","unstructured":"Rafael Valle, Kevin Shih, Ryan Prenger, and Bryan Catanzaro. 2020. Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis. arXiv preprint arXiv:2005.05957 (2020)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413716"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"e_1_3_2_1_30_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 JWeiss, 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_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00754"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"e_1_3_2_1_33_1","volume-title":"Adversarial examples: Attacks and defenses for deep learning","author":"Yuan Xiaoyong","year":"2019","unstructured":"Xiaoyong Yuan, Pan He, Qile Zhu, and Xiaolin Li. 2019. Adversarial examples: Attacks and defenses for deep learning. IEEE transactions on neural networks and learning systems 30, 9 (2019), 2805--2824."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613841","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:54:08Z","timestamp":1755820448000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613841"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":33,"alternative-id":["10.1145\/3581783.3613841","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613841","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}