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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00372898" target="_blank" >RIV/68407700:21230/24:00372898 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.5220/0012391800003636" target="_blank" >https://doi.org/10.5220/0012391800003636</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0012391800003636" target="_blank" >10.5220/0012391800003636</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/VJ02010020" target="_blank" >VJ02010020: AI-Dojo: Multiagentní testbed pro výzkum a testování umělé inteligence v kyberbezpečnosti</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 16th International Conference on Agents and Artificial Intelligence (Volume 3)

ISBN

978-989-758-680-4

ISSN

2184-3589

e-ISSN

2184-433X

Počet stran výsledku

8

Strana od-do

774-781

Název nakladatele

Science and Technology Publications, Lda

Místo vydání

Setúbal

Místo konání akce

Rome

Datum konání akce

24. 2. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—