语音AI代理可自主实施常见诈骗，引发安全担忧。
Voice-Enabled AI Agents can Perform Common Scams
- 基于政府列举的常见骗局，构建可执行诈骗动作的语音代理。
- 实验验证代理能自主完成诈骗所需全部操作步骤。
- 警示语音AI广泛部署前需加强安全管控，适合关注AI伦理者阅读。
近期多模态、高能力大语言模型的发展催生了语音交互式AI代理，拓展了如语音自治客服等新应用。然而，这些能力同样存在双重用途风险。本文选取政府公布的常见诈骗类型，构建具备执行指令的语音代理，并通过实验验证其能自主完成诈骗所需全部行为。结果表明，语音驱动的AI代理具备实施真实诈骗的可行性，引发对语音AI大规模部署的深层安全忧虑。
原文摘要 · Abstract (English)
Recent advances in multi-modal, highly capable LLMs have enabled voice-enabled AI agents. These agents are enabling new applications, such as voice-enabled autonomous customer service. However, with all AI capabilities, these new capabilities have the potential for dual use. In this work, we show that voice-enabled AI agents can perform the actions necessary to perform common scams. To do so, we select a list of common scams collected by the government and construct voice-enabled agents with directions to perform these scams. We conduct experiments on our voice-enabled agents and show that they can indeed perform the actions necessary to autonomously perform such scams. Our results raise questions around the widespread deployment of voice-enabled AI agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。