{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T06:59:16Z","timestamp":1782975556832,"version":"3.54.5"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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":[[2026,5,18]]},"DOI":"10.1109\/sp63933.2026.00150","type":"proceedings-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:34:20Z","timestamp":1782934460000},"page":"1-20","source":"Crossref","is-referenced-by-count":0,"title":["The Person Behind the Sound: Demystifying Audio Private Attribute Profiling Via Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Lixu","family":"Wang","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixiang","family":"Yao","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinfeng","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyao","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"XiaoFeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Dong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/info16080688"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755643"},{"key":"ref5","volume-title":"Homepage of the person behind the sound: Demystifying audio private attribute profiling via multimodal large language models","author":"Authors"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103448"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3546719"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8623.001.0001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2969030"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2022-0002"},{"key":"ref11","first-page":"242","article-title":"Privacy implications of voice and speech analysis-information disclosure by inference","volume-title":"IFIP International Summer School on Privacy and Identity Management","author":"Kr\u00f6ger","year":"2019"},{"key":"ref12","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of Language Resources and Evaluation Conference","author":"Ardila","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57959-7"},{"key":"ref14","article-title":"Mmau: A massive multitask audio understanding and reasoning benchmark","author":"Sakshi","year":"2025","journal-title":"ICLR"},{"key":"ref15","first-page":"196","article-title":"WildDESED: An llm-powered dataset for wild domestic environment sound event detection system","volume-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2024 Workshop","author":"Xiao","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref17","article-title":"Pixabay","volume-title":"Pixabay","year":"2025"},{"key":"ref18","article-title":"Freesound","volume-title":"Freesound","year":"2025"},{"key":"ref19","article-title":"In-context unlearning: Language models as few-shot unlearners","volume-title":"International Conference on Machine Learning","author":"Pawelczyk","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.24457"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560663"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"ref23","article-title":"Qwen2-audio technical report","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Salmonn: Towards generic hearing abilities for large language models","volume-title":"International Conference on Learning Representations","author":"Tang","year":"2024"},{"key":"ref25","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2013-384"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3813-6"},{"key":"ref29","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0705345104"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICTD.2009.5426700"},{"key":"ref32","article-title":"\\{SPEAKE (a) R \\}: Turn speakers to microphones for fun and profit","volume-title":"USENIX Workshop on Offensive Technologies","author":"Guri","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.otc.2019.03.018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.63317\/3o7bccg9xequ"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.79.4.656"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref38","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Soundbible","volume-title":"Soundbible"},{"key":"ref40","article-title":"Zero-shot voice conversion with diffusion transformers","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref42","article-title":"Claude series","year":"2024","journal-title":"Anthropic"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34548"},{"key":"ref44","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2184"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref48","article-title":"Raw waveform-based audio classification using sample-level cnn architectures","volume-title":"Machine Learning for Audio Signal Processing Workshop, Neural Information Processing Systems","author":"Lee","year":"2017"},{"key":"ref49","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418889"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26390-3_37"},{"key":"ref52","article-title":"Robustifying safety-aligned large language models through clean data curation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"SPAVL: A comprehensive safety preference alignment dataset for vision language model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3624010"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27813-7_10"},{"key":"ref56","article-title":"Beyond memorization: Violating privacy via inference with large language models","volume-title":"International Conference on Learning Representations","author":"Staab","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/s24041173"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.30420\/456164008"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2419"},{"key":"ref60","article-title":"Hatman\/audio-emotion-detection","volume-title":"Hatman"}],"event":{"name":"2026 IEEE Symposium on Security and Privacy (SP)","location":"San Francisco, CA, USA","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["2026 IEEE Symposium on Security and Privacy (SP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11573355\/11573356\/11573542.pdf?arnumber=11573542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:27:59Z","timestamp":1782970079000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11573542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/sp63933.2026.00150","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}