ARACNE: An LLM-Based Autonomous Shell Pentesting Agent
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_ | 1866912247113056256 |
|---|---|
| author | Nieponice, Tomas Valeros, Veronica Garcia, Sebastian |
| author_facet | Nieponice, Tomas Valeros, Veronica Garcia, Sebastian |
| contents | We introduce ARACNE, a fully autonomous LLM-based pentesting agent tailored for SSH services that can execute commands on real Linux shell systems. Introduces a new agent architecture with multi-LLM model support. Experiments show that ARACNE can reach a 60\% success rate against the autonomous defender ShelLM and a 57.58\% success rate against the Over The Wire Bandit CTF challenges, improving over the state-of-the-art. When winning, the average number of actions taken by the agent to accomplish the goals was less than 5. The results show that the use of multi-LLM is a promising approach to increase accuracy in the actions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18528 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ARACNE: An LLM-Based Autonomous Shell Pentesting Agent Nieponice, Tomas Valeros, Veronica Garcia, Sebastian Cryptography and Security Artificial Intelligence Robotics We introduce ARACNE, a fully autonomous LLM-based pentesting agent tailored for SSH services that can execute commands on real Linux shell systems. Introduces a new agent architecture with multi-LLM model support. Experiments show that ARACNE can reach a 60\% success rate against the autonomous defender ShelLM and a 57.58\% success rate against the Over The Wire Bandit CTF challenges, improving over the state-of-the-art. When winning, the average number of actions taken by the agent to accomplish the goals was less than 5. The results show that the use of multi-LLM is a promising approach to increase accuracy in the actions. |
| title | ARACNE: An LLM-Based Autonomous Shell Pentesting Agent |
| topic | Cryptography and Security Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2502.18528 |