SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Adebimpe, Adetayo, Neukirchen, Helmut, Welsh, Thomas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914425716342784
author Adebimpe, Adetayo
Neukirchen, Helmut
Welsh, Thomas
author_facet Adebimpe, Adetayo
Neukirchen, Helmut
Welsh, Thomas
contents Honeypots are decoy systems used for gathering valuable threat intelligence or diverting attackers away from production systems. Maximising attacker engagement is essential to their utility. However research has highlighted that context-awareness, such as the ability to respond to new attack types, systems and attacker agents, is necessary to increase engagement. Large Language Models (LLMs) have been shown as one approach to increase context awareness but suffer from several challenges including accuracy and timeliness of response time, high operational costs and data-protection issues due to cloud deployment. We propose the System-Based Attention Shell Honeypot (SBASH) framework which manages data-protection issues through the use of lightweight local LLMs. We investigate the use of Retrieval Augmented Generation (RAG) supported LLMs and non-RAG LLMs for Linux shell commands and evaluate them using several different metrics such as response time differences, realism from human testers, and similarity to a real system calculated with Levenshtein distance, SBert, and BertScore. We show that RAG improves accuracy for untuned models while models that have been tuned via a system prompt that tells the LLM to respond like a Linux system achieve without RAG a similar accuracy as untuned with RAG, while having a slightly lower latency.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21459
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots
Adebimpe, Adetayo
Neukirchen, Helmut
Welsh, Thomas
Cryptography and Security
Computation and Language
Machine Learning
K.6.5; D.4.6; I.2.7
Honeypots are decoy systems used for gathering valuable threat intelligence or diverting attackers away from production systems. Maximising attacker engagement is essential to their utility. However research has highlighted that context-awareness, such as the ability to respond to new attack types, systems and attacker agents, is necessary to increase engagement. Large Language Models (LLMs) have been shown as one approach to increase context awareness but suffer from several challenges including accuracy and timeliness of response time, high operational costs and data-protection issues due to cloud deployment. We propose the System-Based Attention Shell Honeypot (SBASH) framework which manages data-protection issues through the use of lightweight local LLMs. We investigate the use of Retrieval Augmented Generation (RAG) supported LLMs and non-RAG LLMs for Linux shell commands and evaluate them using several different metrics such as response time differences, realism from human testers, and similarity to a real system calculated with Levenshtein distance, SBert, and BertScore. We show that RAG improves accuracy for untuned models while models that have been tuned via a system prompt that tells the LLM to respond like a Linux system achieve without RAG a similar accuracy as untuned with RAG, while having a slightly lower latency.
title SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots
topic Cryptography and Security
Computation and Language
Machine Learning
K.6.5; D.4.6; I.2.7
url https://arxiv.org/abs/2510.21459