Voice-Enabled AI Agents can Perform Common Scams

TL;DR

This paper demonstrates that voice-enabled AI agents, empowered by advanced language models, can autonomously perform common scams, raising concerns about their potential misuse and the need for safeguards.

Contribution

It is the first to show that voice-enabled AI agents can autonomously execute common scams, highlighting new risks associated with these technologies.

Findings

Voice-enabled AI agents can perform common scams autonomously.

Experiments confirm the feasibility of scam execution by AI agents.

Raises concerns about misuse and safety of voice-enabled AI systems.

Abstract

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.