VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913661923098624 |
|---|---|
| author | Kong, He Hu, Die Ge, Jingguo Li, Liangxiong Li, Tong Wu, Bingzhen |
| author_facet | Kong, He Hu, Die Ge, Jingguo Li, Liangxiong Li, Tong Wu, Bingzhen |
| contents | Penetration testing is a vital practice for identifying and mitigating vulnerabilities in cybersecurity systems, but its manual execution is labor-intensive and time-consuming. Existing large language model (LLM)-assisted or automated penetration testing approaches often suffer from inefficiencies, such as a lack of contextual understanding and excessive, unstructured data generation. This paper presents VulnBot, an automated penetration testing framework that leverages LLMs to simulate the collaborative workflow of human penetration testing teams through a multi-agent system. To address the inefficiencies and reliance on manual intervention in traditional penetration testing methods, VulnBot decomposes complex tasks into three specialized phases: reconnaissance, scanning, and exploitation. These phases are guided by a penetration task graph (PTG) to ensure logical task execution. Key design features include role specialization, penetration path planning, inter-agent communication, and generative penetration behavior. Experimental results demonstrate that VulnBot outperforms baseline models such as GPT-4 and Llama3 in automated penetration testing tasks, particularly showcasing its potential in fully autonomous testing on real-world machines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13411 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework Kong, He Hu, Die Ge, Jingguo Li, Liangxiong Li, Tong Wu, Bingzhen Software Engineering Penetration testing is a vital practice for identifying and mitigating vulnerabilities in cybersecurity systems, but its manual execution is labor-intensive and time-consuming. Existing large language model (LLM)-assisted or automated penetration testing approaches often suffer from inefficiencies, such as a lack of contextual understanding and excessive, unstructured data generation. This paper presents VulnBot, an automated penetration testing framework that leverages LLMs to simulate the collaborative workflow of human penetration testing teams through a multi-agent system. To address the inefficiencies and reliance on manual intervention in traditional penetration testing methods, VulnBot decomposes complex tasks into three specialized phases: reconnaissance, scanning, and exploitation. These phases are guided by a penetration task graph (PTG) to ensure logical task execution. Key design features include role specialization, penetration path planning, inter-agent communication, and generative penetration behavior. Experimental results demonstrate that VulnBot outperforms baseline models such as GPT-4 and Llama3 in automated penetration testing tasks, particularly showcasing its potential in fully autonomous testing on real-world machines. |
| title | VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2501.13411 |