Saved in:
Bibliographic Details
Main Authors: Fang, Richard, Bowman, Dylan, Kang, Daniel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15650
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910658063237120
author Fang, Richard
Bowman, Dylan
Kang, Daniel
author_facet Fang, Richard
Bowman, Dylan
Kang, Daniel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15650
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Voice-Enabled AI Agents can Perform Common Scams
Fang, Richard
Bowman, Dylan
Kang, Daniel
Artificial Intelligence
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.
title Voice-Enabled AI Agents can Perform Common Scams
topic Artificial Intelligence
url https://arxiv.org/abs/2410.15650