Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
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_ | 1866910974387159040 |
|---|---|
| author | Zhang, Hanrong Huang, Jingyuan Mei, Kai Yao, Yifei Wang, Zhenting Zhan, Chenlu Wang, Hongwei Zhang, Yongfeng |
| author_facet | Zhang, Hanrong Huang, Jingyuan Mei, Kai Yao, Yifei Wang, Zhenting Zhan, Chenlu Wang, Hongwei Zhang, Yongfeng |
| contents | Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature does not comprehensively evaluate attacks and defenses against LLM-based agents. To address this, we introduce Agent Security Bench (ASB), a comprehensive framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents, including 10 scenarios (e.g., e-commerce, autonomous driving, finance), 10 agents targeting the scenarios, over 400 tools, 27 different types of attack/defense methods, and 7 evaluation metrics. Based on ASB, we benchmark 10 prompt injection attacks, a memory poisoning attack, a novel Plan-of-Thought backdoor attack, 4 mixed attacks, and 11 corresponding defenses across 13 LLM backbones. Our benchmark results reveal critical vulnerabilities in different stages of agent operation, including system prompt, user prompt handling, tool usage, and memory retrieval, with the highest average attack success rate of 84.30\%, but limited effectiveness shown in current defenses, unveiling important works to be done in terms of agent security for the community. We also introduce a new metric to evaluate the agents' capability to balance utility and security. Our code can be found at https://github.com/agiresearch/ASB. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02644 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Zhang, Hanrong Huang, Jingyuan Mei, Kai Yao, Yifei Wang, Zhenting Zhan, Chenlu Wang, Hongwei Zhang, Yongfeng Cryptography and Security Artificial Intelligence Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature does not comprehensively evaluate attacks and defenses against LLM-based agents. To address this, we introduce Agent Security Bench (ASB), a comprehensive framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents, including 10 scenarios (e.g., e-commerce, autonomous driving, finance), 10 agents targeting the scenarios, over 400 tools, 27 different types of attack/defense methods, and 7 evaluation metrics. Based on ASB, we benchmark 10 prompt injection attacks, a memory poisoning attack, a novel Plan-of-Thought backdoor attack, 4 mixed attacks, and 11 corresponding defenses across 13 LLM backbones. Our benchmark results reveal critical vulnerabilities in different stages of agent operation, including system prompt, user prompt handling, tool usage, and memory retrieval, with the highest average attack success rate of 84.30\%, but limited effectiveness shown in current defenses, unveiling important works to be done in terms of agent security for the community. We also introduce a new metric to evaluate the agents' capability to balance utility and security. Our code can be found at https://github.com/agiresearch/ASB. |
| title | Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2410.02644 |