{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T12:35:43Z","timestamp":1785328543516,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["PE00000014"],"award-info":[{"award-number":["PE00000014"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746265.3759668","type":"proceedings-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T22:20:29Z","timestamp":1759962029000},"page":"101-109","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Reliable Audio Deepfake Attribution and Model Recognition: A Multi-Level Autoencoder-Based Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6279-9212","authenticated-orcid":false,"given":"Andrea","family":"Di Pierno","sequence":"first","affiliation":[{"name":"IMT School of Advanced Studies, Lucca, Tuscany, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8315-351X","authenticated-orcid":false,"given":"Luca","family":"Guarnera","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Catania, Catania, Sicily, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4819-5340","authenticated-orcid":false,"given":"Dario","family":"Allegra","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Catania, Catania, Sicily, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6127-2470","authenticated-orcid":false,"given":"Sebastiano","family":"Battiato","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Catania, Catania, Sicily, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tania Sari Bonaventura","author":"Amerini Irene","year":"2025","unstructured":"Irene Amerini, Mauro Barni, Sebastiano Battiato, Paolo Bestagini, Giulia Boato, Tania Sari Bonaventura, Vittoria Bruni, Roberto Caldelli, Francesco De Natale, Rocco De Nicola, Luca Guarnera, Sara Mandelli, Gian Luca Marcialis, Marco Micheletto, Andrea Montibeller, Giulia Orr\u00f9, Alessandro Ortis, Pericle Perazzo, Giovanni Puglisi, Davide Salvi, Stefano Tubaro, Claudia Melis Tonti, Massimo Villari, and Domenico Vitulano. 2025. Deepfake Media Forensics: State of the Art and Challenges Ahead. In Advances in Social Networks Analysis and Mining, I-Hsien Ting, Reda Alhajj, Panagiotis Karampelas, and Min-Yuh Day (Eds.). Springer Nature Switzerland, Cham, 33-48."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsidi.2024.301795"},{"key":"e_1_3_2_1_3_1","volume-title":"ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection. arXiv:1812.02510","author":"Cozzolino Davide","year":"2019","unstructured":"Davide Cozzolino, Justus Thies, Andreas R\u00f6ssler, Christian Riess, Matthias Nie\u00dfner, and Luisa Verdoliva. 2019. ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection. arXiv:1812.02510 (2019). arXiv:1812.02510 [cs.CV]"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2650"},{"key":"e_1_3_2_1_5_1","unstructured":"Zhihao Du Shiliang Zhang Kai Hu and Siqi Zheng. 2023. FunCodec: A Fundamental Reproducible and Integrable Open-source Toolkit for Neural Speech Codec. arXiv:2309.07405 [cs.SD]"},{"key":"e_1_3_2_1_6_1","unstructured":"Alexandre D\u00e9fossez Jade Copet Gabriel Synnaeve and Yossi Adi. 2022. High Fidelity Neural Audio Compression. arXiv:2210.13438 [eess.AS]"},{"key":"e_1_3_2_1_7_1","volume-title":"Tomi Kinnunen, and Kamil Malinka.","author":"Firc Anton","year":"2025","unstructured":"Anton Firc, Manasi Chibber, Jagabandhu Mishra, Vishwanath Pratap Singh, Tomi Kinnunen, and Kamil Malinka. 2025. STOPA: A Database of Systematic VariaTion Of DeePfake Audio for Open-Set Source Tracing and Attribution. arXiv:2505.19644 (2025)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652027"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops.","author":"Guarnera Luca","year":"2020","unstructured":"Luca Guarnera, Oliver Giudice, Matthias Niessner, and Sebastiano Battiato. 2020. On the Exploitation of Deepfake Model Recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCIS63231.2024.10931997"},{"key":"e_1_3_2_1_11_1","first-page":"1268","article-title":"RawNet","volume":"2019","author":"Kim Hee-Soo","year":"2019","unstructured":"Jee-weon Jung, Hee-Soo Kim, Hye-jin Kim, Sung-Hyun Yoon, and Ha-Jin Yu. 2019. RawNet: Advanced End-to-End Deep Neural Network Using Raw Waveforms for Text-Independent Speaker Verification. In Interspeech 2019. 1268-1272.","journal-title":"In Interspeech"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1283"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3285283"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Nicolas M\u00fcller Pavel Czempin Franziska Diekmann Adam Froghyar and Konstantin B\u00f6ttinger. 2022. Does Audio Deepfake Detection Generalize?. In Interspeech.","DOI":"10.21437\/Interspeech.2022-108"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-129"},{"key":"e_1_3_2_1_16_1","volume-title":"Harder or Different? Understanding Generalization of Audio Deepfake Detection. arXiv:2406.03512","author":"M\u00fcller Nicolas M.","year":"2024","unstructured":"Nicolas M. M\u00fcller, Nicholas Evans, Hemlata Tak, Philip Sperl, and Konstantin B\u00f6ttinger. 2024. Harder or Different? Understanding Generalization of Audio Deepfake Detection. arXiv:2406.03512 (2024). arXiv:2406.03512 [cs.SD]"},{"key":"e_1_3_2_1_17_1","volume-title":"Shivkumar Chandrasekaran, Arjuna Flenner, Jawadul H. Bappy, Amit K. Roy-Chowdhury, and B. S. Manjunath.","author":"Nataraj Lakshmanan","year":"2019","unstructured":"Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Shivkumar Chandrasekaran, Arjuna Flenner, Jawadul H. Bappy, Amit K. Roy-Chowdhury, and B. S. Manjunath. 2019. Detecting GAN generated Fake Images using Co-occurrence Matrices. arXiv:1903.06836 (2019). arXiv:1903.06836 [cs.CV]"},{"key":"e_1_3_2_1_18_1","volume-title":"Source Verification for Speech Deepfakes. arXiv:2505.14188","author":"Negroni Viola","year":"2025","unstructured":"Viola Negroni, Davide Salvi, Paolo Bestagini, and Stefano Tubaro. 2025. Source Verification for Speech Deepfakes. arXiv:2505.14188 (2025)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/EUVIP53989.2022.9922861"},{"key":"e_1_3_2_1_20_1","volume-title":"Arun Balaji Buduru, and Rajesh Sharma.","author":"Phukan Orchid Chetia","year":"2024","unstructured":"Orchid Chetia Phukan, Drishti Singh, Swarup Ranjan Behera, Arun Balaji Buduru, and Rajesh Sharma. 2024. Investigating Prosodic Signatures via Speech Pre?Trained Models for Audio Deepfake Source Attribution. In arXiv preprint. arXiv:2412.17796."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/icip51287.2024.10648013"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906599"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"e_1_3_2_1_24_1","volume-title":"TADA: Training-free Attribution and Out-of-Domain Detection of Audio Deepfakes. arXiv:2506.05802","author":"Stan Adriana","year":"2025","unstructured":"Adriana Stan, David Combei, Dan Oneata, and Horia Cucu. 2025. TADA: Training-free Attribution and Out-of-Domain Detection of Audio Deepfakes. arXiv:2506.05802 (2025). arXiv:2506.05802 [eess.AS]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"e_1_3_2_1_26_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. 2020. ASVspoof 2019: A large-scale public database of synthesized converted and replayed speech. arXiv:1911.01601 (2020). arXiv:1911.01601 [eess.AS]","DOI":"10.1016\/j.csl.2020.101114"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889399"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2093"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096509"},{"key":"e_1_3_2_1_30_1","volume-title":"Audio Deepfake Attribution: An Initial Dataset and Investigation. arXiv:2208.10489","author":"Yan Xinrui","year":"2022","unstructured":"Xinrui Yan, Jiangyan Yi, Jianhua Tao, and Jie Chen. 2022. Audio Deepfake Attribution: An Initial Dataset and Investigation. arXiv:2208.10489 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP63861.2024.10800741"},{"key":"e_1_3_2_1_32_1","unstructured":"Dongchao Yang Songxiang Liu Rongjie Huang Jinchuan Tian Chao Weng and Yuexian Zou. 2023. HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec. arXiv:2305.02765 [cs.SD]"},{"key":"e_1_3_2_1_33_1","volume-title":"Chu Yuan Zhang, and Yan Zhao","author":"Yi Jiangyan","year":"2023","unstructured":"Jiangyan Yi, Chenglong Wang, Jianhua Tao, Xiaohui Zhang, Chu Yuan Zhang, and Yan Zhao. 2023. Audio Deepfake Detection: A Survey. arXiv:2308.14970 (2023). arXiv:2308.14970 [cs.SD]"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Neil Zeghidour Alejandro Luebs Ahmed Omran Jan Skoglund and Marco Tagliasacchi. 2021. SoundStream: An End-to-End Neural Audio Codec. arXiv:2107.03312 [cs.SD]","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"e_1_3_2_1_35_1","unstructured":"Xin Zhang Dong Zhang Shimin Li Yaqian Zhou and Xipeng Qiu. 2024. SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models. arXiv:2308.16692 [cs.CL]"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 1st on Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746265.3759668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:51:29Z","timestamp":1764550289000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746265.3759668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":35,"alternative-id":["10.1145\/3746265.3759668","10.1145\/3746265"],"URL":"https:\/\/doi.org\/10.1145\/3746265.3759668","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}