The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915590270091264 |
|---|---|
| author | He, Feng Zhu, Tianqing Ye, Dayong Liu, Bo Zhou, Wanlei Yu, Philip S. |
| author_facet | He, Feng Zhu, Tianqing Ye, Dayong Liu, Bo Zhou, Wanlei Yu, Philip S. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_19354 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies He, Feng Zhu, Tianqing Ye, Dayong Liu, Bo Zhou, Wanlei Yu, Philip S. Cryptography and Security 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. |
| title | The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2407.19354 |