Security of AI Agents

Yifeng He, Ethan Wang, Yuyang Rong, Zifei Cheng, Hao Chen
6/12/2024
cs.CRcs.AI

No official code found. Best implementation: SecurityLab-UCD/ai-agent-security (6 stars, last commit 2024-12-15).

Abstract

AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through studying and experiencing the workflow of typical AI agents, we have raised several concerns regarding their security. These potential vulnerabilities are not addressed by the frameworks used to build the agents, nor by research aimed at improving the agents. In this paper, we identify and describe these vulnerabilities in detail from a system security perspective, emphasizing their causes and severe effects. Furthermore, we introduce defense mechanisms corresponding to each vulnerability with design and experiments to evaluate their viability. Altogether, this paper contextualizes the security issues in the current development of AI agents and delineates methods to make AI agents safer and more reliable.

View on arXivView PDF

Code Implementations(1)

SecurityLab-UCD/ai-agent-securityCommunity100%

[RAIE'25] This repository contains source code for the demos and attacks we present in our paper `Security of AI Agents`.

62Shell, PythonApr 18, 20241 years ago
ai-agentsencryptionicse2025raie2025security-analysis

Similar Papers

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows

87% match2025

Safeguarding AI Agents: Developing and Analyzing Safety Architectures

87% match2024

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms

86% match2025

A Survey of Attacks on Large Language Models

86% match2025

The Dark Side of LLMs: Agent-based Attacks for Complete Computer Takeover

86% match2025

Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems

85% match2025

Cite this paper

@article{he2024security,
  title  = {Security of AI Agents},
  author = {Yifeng He and Ethan Wang and Yuyang Rong and Zifei Cheng and Hao Chen},
  year   = {2024},
  eprint = {2406.08689},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.08689v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.08689.svg)](https://codeofpaper.com/paper/2406.08689)

Discussion