Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments

Maria Rigaki, Ondřej Lukáš, Carlos Catania, Sebastian Garcia

2024

Abstract

Large Language Models (LLMs) have gained widespread popularity across diverse domains involving text generation, summarization, and various natural language processing tasks. Despite their inherent limitations, LLM-based designs have shown promising capabilities in planning and navigating open-world scenarios. This paper introduces a novel application of pre-trained LLMs as agents within cybersecurity network environments, focusing on their utility for sequential decision-making processes. We present an approach wherein pre-trained LLMs are leveraged as attacking agents in two reinforcement learning environments. Our proposed agents demonstrate similar or better performance against state-of-the-art agents trained for thousands of episodes in most scenarios and configurations. In addition, the best LLM agents perform similarly to human testers of the environment without any additional training process. This design highlights the potential of LLMs to address complex decision-making tasks within cybersecurity efficiently. Furthermore, we introduce a new network security environment named NetSecGame. The environment is designed to support complex multi-agent scenarios within the network security domain eventually. The proposed environment mimics real network attacks and is designed to be highly modular and adaptable for various scenarios.

Paper Citation

in Harvard Style

Rigaki M., Lukáš O., Catania C. and Garcia S. (2024). Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 774-781. DOI: 10.5220/0012391800003636

in Bibtex Style

@conference{icaart24,
author={Maria Rigaki and Ondřej Lukáš and Carlos Catania and Sebastian Garcia},
title={Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={774-781},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012391800003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
SN - 978-989-758-680-4
AU - Rigaki M.
AU - Lukáš O.
AU - Catania C.
AU - Garcia S.
PY - 2024
SP - 774
EP - 781
DO - 10.5220/0012391800003636
PB - SciTePress