{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:48:40Z","timestamp":1772632120510,"version":"3.50.1"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1109\/ijcb65343.2025.11410761","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:50:39Z","timestamp":1772571039000},"page":"1-11","source":"Crossref","is-referenced-by-count":0,"title":["Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection"],"prefix":"10.1109","author":[{"given":"Akanksha","family":"Chuchra","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Ropar,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shukesh","family":"Reddy","sequence":"additional","affiliation":[{"name":"Birla Institute of Technology and Science,Machine Intelligence Group,Pilani,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sudeepta","family":"Mishra","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Ropar,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhijit","family":"Das","sequence":"additional","affiliation":[{"name":"Birla Institute of Technology and Science,Machine Intelligence Group,Pilani,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Dhall","sequence":"additional","affiliation":[{"name":"Monash University,Melbourne,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s25071989"},{"key":"ref2","article-title":"Audio deepfake detection: A survey","author":"Yi","year":"2023"},{"key":"ref3","article-title":"Add 2023: Towards audio deepfake detection and analysis in the wild","author":"Yi","year":"2024","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/3300000048"},{"key":"ref5","article-title":"I can hear you: Selective robust training for deepfake audio detection","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref8","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.160"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447923"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1537"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3547861"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3649506"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref18","article-title":"Next-gpt: Any-to-any multimodal llm","volume-title":"Forty-first International Conference on Machine Learning","author":"Wu"},{"key":"ref19","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4783140","article-title":"Exploring the frontier of vision-language models: A survey of current methodologies and future directions","author":"Ghosh","year":"2024"},{"key":"ref23","article-title":"Survey on ai-generated media detection: From non-mllm to mllm","author":"Zou","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00436"},{"key":"ref25","article-title":"Unlocking the capabilities of vision-language models for gener-alizable and explainable deepfake detection","author":"Yu","year":"2025"},{"key":"ref26","article-title":"Antifake-prompt: Prompt-tuned vision-language models are fake image detectors","author":"Chang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448257"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.109"},{"key":"ref29","article-title":"Gpt-4 technical report","year":"2024"},{"key":"ref30","article-title":"Deepseek-v3 technical report","year":"2025"},{"key":"ref31","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref34","article-title":"Beats: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022"},{"key":"ref35","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref37","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-698"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096278"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3233005"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163888"},{"key":"ref43","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889251"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref51","article-title":"Qwen2-audio technical report","author":"Chu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-457"},{"key":"ref53","article-title":"Salmonn: Towards generic hearing abilities for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-968"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446343"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.974"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1561\/116.20250004"},{"issue":"2","key":"ref59","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2025.100757"}],"event":{"name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","location":"Osaka, Japan","start":{"date-parts":[[2025,9,8]]},"end":{"date-parts":[[2025,9,11]]}},"container-title":["2025 IEEE International Joint Conference on Biometrics (IJCB)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11410556\/11410616\/11410761.pdf?arnumber=11410761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T06:51:54Z","timestamp":1772607114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11410761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/ijcb65343.2025.11410761","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]}}}