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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Rigaki, Maria, Lukáš, Ondřej, Catania, Carlos A., Garcia, Sebastian
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866907867420819456
author Rigaki, Maria
Lukáš, Ondřej
Catania, Carlos A.
Garcia, Sebastian
author_facet Rigaki, Maria
Lukáš, Ondřej
Catania, Carlos A.
Garcia, Sebastian
contents 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 efficiently address complex decision-making tasks within cybersecurity. Furthermore, we introduce a new network security environment named NetSecGame. The environment is designed to eventually support complex multi-agent scenarios within the network security domain. The proposed environment mimics real network attacks and is designed to be highly modular and adaptable for various scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2308_12086
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
Rigaki, Maria
Lukáš, Ondřej
Catania, Carlos A.
Garcia, Sebastian
Cryptography and Security
Artificial Intelligence
Computation and Language
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 efficiently address complex decision-making tasks within cybersecurity. Furthermore, we introduce a new network security environment named NetSecGame. The environment is designed to eventually support complex multi-agent scenarios within the network security domain. The proposed environment mimics real network attacks and is designed to be highly modular and adaptable for various scenarios.
title Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
topic Cryptography and Security
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2308.12086