{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T22:59:45Z","timestamp":1773356385214,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,21]]},"DOI":"10.1145\/3643651.3659894","type":"proceedings-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T00:20:03Z","timestamp":1718065203000},"page":"35-36","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Review of Existing Methods for Generating and Detecting Fake and Partially Fake Audio"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9752-2481","authenticated-orcid":false,"given":"Abdulazeez","family":"Alali","sequence":"first","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2701-7809","authenticated-orcid":false,"given":"George","family":"Theodorakopoulos","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Polyvit: Co-training vision transformers on images, videos and audio,\" arXiv preprint arXiv:2111.12993","author":"Likhosherstov V.","year":"2021","unstructured":"V. Likhosherstov, A. Arnab, K. Choromanski, M. Lucic, Y. Tay, A. Weller, and M. Dehghani, \"Polyvit: Co-training vision transformers on images, videos and audio,\" arXiv preprint arXiv:2111.12993, 2021."},{"key":"e_1_3_2_1_2_1","volume-title":"Ast: Audio spectrogram transformer,\" arXiv preprint arXiv:2104.01778","author":"Gong Y.","year":"2021","unstructured":"Y. Gong, Y.-A. Chung, and J. Glass, \"Ast: Audio spectrogram transformer,\" arXiv preprint arXiv:2104.01778, 2021."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11733-y"},{"key":"e_1_3_2_1_4_1","volume-title":"Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review,\" arXiv preprint arXiv:2208.10913","author":"Altuncu E.","year":"2022","unstructured":"E. Altuncu, V. N. Franqueira, and S. Li, \"Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review,\" arXiv preprint arXiv:2208.10913, 2022."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13322"},{"key":"e_1_3_2_1_6_1","volume-title":"A survey on audio diffusion models: Text to speech synthesis and enhancement in generative ai,\" arXiv preprint arXiv:2303.13336","author":"Zhang C.","year":"2023","unstructured":"C. Zhang, C. Zhang, S. Zheng, M. Zhang, M. Qamar, S.-H. Bae, and I. S. Kweon, \"A survey on audio diffusion models: Text to speech synthesis and enhancement in generative ai,\" arXiv preprint arXiv:2303.13336, vol. 2, 2023."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13943-4"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13053100"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/a15050155"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2022.1001063"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03766-z"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"e_1_3_2_1_14_1","first-page":"6820","volume-title":"Cyclegan-vc2: Improved cyclegan-based non-parallel voice conversion","author":"Kaneko T.","unstructured":"T. Kaneko, H. Kameoka, K. Tanaka, and N. Hojo, \"Cyclegan-vc2: Improved cyclegan-based non-parallel voice conversion.\" pp. 6820--6824."},{"key":"e_1_3_2_1_15_1","first-page":"552","volume-title":"Adversarial attack on voice conversion","author":"Huang C.-y.","unstructured":"C.-y. Huang, Y. Y. Lin, H.-y. Lee, and L.-s. Lee, \"Defending your voice: Adversarial attack on voice conversion.\" pp. 552--559."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5772\/2391"}],"event":{"name":"CODASPY '24: Fourteenth ACM Conference on Data and Application Security and Privacy","location":"Porto Portugal","acronym":"CODASPY '24","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 10th ACM International Workshop on Security and Privacy Analytics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643651.3659894","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3643651.3659894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:32:03Z","timestamp":1755973923000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643651.3659894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":16,"alternative-id":["10.1145\/3643651.3659894","10.1145\/3643651"],"URL":"https:\/\/doi.org\/10.1145\/3643651.3659894","relation":{},"subject":[],"published":{"date-parts":[[2024,6,19]]},"assertion":[{"value":"2024-06-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}