模型能听到你：音频语言模型的部署应考虑最小权限原则
The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege
AI总结：
本文指出端到端音频语言模型相比级联流水线带来身份推断等社会技术安全风险，主张以最小权限原则指导其开发与部署，并强调现有基准的不足。
摘要：
最新的音频语言模型（Audio LMs）直接处理语音，而非依赖单独的转录步骤。这一转变保留了详细信息，如语调或多个说话者的存在，这些信息在转录中可能会丢失。然而，这也引入了新的安全风险，包括说话者身份线索和其他敏感声音属性的潜在滥用，这可能带来法律影响。在本文中，我们敦促更仔细地审视这些模型的构建和部署方式。我们的实验表明，与级联流水线相比，端到端建模产生了社会技术安全风险，如身份推断、偏见决策和情绪检测。这引发了关于音频语言模型是否存储声纹并以在现有法律体制下造成不确定性的方式运作的担忧。随后，我们主张应考虑最小权限原则来指导这些模型的开发与部署。具体而言，评估应考察（1）与端到端建模相关的隐私和安全风险；（2）信息访问的适当范围。最后，我们强调了当前音频语言模型基准中的相关空白，并指出了必须解决的关键开放研究问题，包括技术性和政策性的，以实现端到端音频语言模型的负责任部署。
英文摘要：
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 intonation 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, both technical and policy-related, that must be addressed to enable the responsible deployment of end-to-end Audio LMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
