LLM in the Shell: Generative Honeypots

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00380657" target="_blank" >RIV/68407700:21230/24:00380657 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/EuroSPW61312.2024.00054" target="_blank" >https://doi.org/10.1109/EuroSPW61312.2024.00054</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/EuroSPW61312.2024.00054" target="_blank" >10.1109/EuroSPW61312.2024.00054</a>

Jazyk výsledku

angličtina

Název v původním jazyce

LLM in the Shell: Generative Honeypots

Popis výsledku v původním jazyce

Honeypots are essential tools in cybersecurity for early detection, threat intelligence gathering, and analysis of attacker's behavior. However, most of them lack the required realism to engage and fool human attackers long-term. Being easy to distinguish honeypots strongly hinders their effectiveness. This can happen because they are too deterministic, lack adaptability, or lack deepness. This work introduces shelLM, a dynamic and realistic software honeypot based on Large Language Models that generates Linux-like shell output. We designed and implemented shelLM using cloud-based LLMs. We evaluated if shelLM can generate output as expected from a real Linux shell. The evaluation was done by asking cybersecurity researchers to use the honeypot and give feedback if each answer from the honeypot was the expected one from a Linux shell. Results indicate that shelLM can create credible and dynamic answers capable of addressing the limitations of current honeypots. ShelLM reached a TNR of 0.90, convincing humans it was consistent with a real Linux shell. The source code and prompts for replicating the experiments have been publicly available.

Název v anglickém jazyce

LLM in the Shell: Generative Honeypots

Popis výsledku anglicky

Honeypots are essential tools in cybersecurity for early detection, threat intelligence gathering, and analysis of attacker's behavior. However, most of them lack the required realism to engage and fool human attackers long-term. Being easy to distinguish honeypots strongly hinders their effectiveness. This can happen because they are too deterministic, lack adaptability, or lack deepness. This work introduces shelLM, a dynamic and realistic software honeypot based on Large Language Models that generates Linux-like shell output. We designed and implemented shelLM using cloud-based LLMs. We evaluated if shelLM can generate output as expected from a real Linux shell. The evaluation was done by asking cybersecurity researchers to use the honeypot and give feedback if each answer from the honeypot was the expected one from a Linux shell. Results indicate that shelLM can create credible and dynamic answers capable of addressing the limitations of current honeypots. ShelLM reached a TNR of 0.90, convincing humans it was consistent with a real Linux shell. The source code and prompts for replicating the experiments have been publicly available.

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

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings - 9th IEEE European Symposium on Security and Privacy Workshops, Euro S and PW 2024

ISBN

979-8-3503-6729-4

ISSN

2768-0649

e-ISSN

2768-0657

Počet stran výsledku

6

Strana od-do

430-435

Název nakladatele

IEEE Computer Society

Místo vydání

Cannes

Místo konání akce

Vídeň

Datum konání akce

8. 7. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001302657400048