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.
@article{arxiv.2410.15650,
title = {Voice-Enabled AI Agents can Perform Common Scams},
author = {Richard Fang and Dylan Bowman and Daniel Kang},
journal= {arXiv preprint arXiv:2410.15650},
year = {2024}
}