The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies

TL;DR

This survey reviews emerging security and privacy challenges of LLM agents, analyzing threats, impacts, defenses, and future trends, supported by case studies to guide future research and improve trustworthiness.

Contribution

It provides a comprehensive overview of security and privacy issues in LLM agents, including threat categorization, impacts, defenses, and future directions, with case studies illustrating key points.

Findings

Identification of key security threats to LLM agents

Analysis of privacy vulnerabilities and their impacts

Review of current defense strategies and future trends

Abstract

Inspired by the rapid development of Large Language Models (LLMs), LLM agents have evolved to perform complex tasks. LLM agents are now extensively applied across various domains, handling vast amounts of data to interact with humans and execute tasks. The widespread applications of LLM agents demonstrate their significant commercial value; however, they also expose security and privacy vulnerabilities. At the current stage, comprehensive research on the security and privacy of LLM agents is highly needed. This survey aims to provide a comprehensive overview of the newly emerged privacy and security issues faced by LLM agents. We begin by introducing the fundamental knowledge of LLM agents, followed by a categorization and analysis of the threats. We then discuss the impacts of these threats on humans, environment, and other agents. Subsequently, we review existing defensive strategies, and finally explore future trends. Additionally, the survey incorporates diverse case studies to facilitate a more accessible understanding. By highlighting these critical security and privacy issues, the survey seeks to stimulate future research towards enhancing the security and privacy of LLM agents, thereby increasing their reliability and trustworthiness in future applications.