{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:47:36Z","timestamp":1760575656397,"version":"build-2065373602"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIES"],"abstract":"<jats:p>The latest Audio Language Models (Audio LMs) process speech directly instead of relying on a separate transcription step. This shift preserves detailed information, such as into-\nnation or the presence of multiple speakers, that would otherwise be lost in transcription. However, it also introduces new safety risks, including the potential misuse of speaker identity cues and other sensitive vocal attributes, which could have legal implications. In this paper, we urge a closer examination of how these models are built and deployed. Our experiments show that end-to-end modeling, compared with cascaded pipelines, creates socio-technical safety risks such as identity inference, biased decision-making, and emotion detection. This raises concerns about whether Audio LMs store voiceprints and function in ways that create uncertainty under existing legal regimes. We then argue that the Principle of Least Privilege should be considered to guide the development and deployment of these models. Specifically, evaluations should assess (1) the privacy and safety risks associated with end-to-end modeling; and (2) the appropriate scope of information access. Finally, we highlight related gaps in current audio LM benchmarks and identify key open research questions\u2014both technical and policy-related\u2014that must be addressed to enable the responsible deployment of end-to-end Audio LMs.<\/jats:p>","DOI":"10.1609\/aies.v8i2.36625","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:20:40Z","timestamp":1760534440000},"page":"1231-1244","source":"Crossref","is-referenced-by-count":0,"title":["The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege"],"prefix":"10.1609","volume":"8","author":[{"given":"Luxi","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michel","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inyoung","family":"Cheong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prateek","family":"Mittal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danqi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Henderson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2025,10,15]]},"container-title":["Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36625\/38763","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36625\/38763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:20:40Z","timestamp":1760534440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/view\/36625"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":0,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,10,15]]}},"URL":"https:\/\/doi.org\/10.1609\/aies.v8i2.36625","relation":{},"ISSN":["3065-8365"],"issn-type":[{"value":"3065-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}