Sep 2026· International Journal of Information Security· Vol 25· 1 citation· 70 references
Computer Science
TL;DR
HIVE-AI, a 47,578-LoC honeypot framework deployed continuously on a single 4-vCPU/4-GB Virtual Private Server since 6 April 2026, is presented, a promising low-cost alternative rather than a full substitute for open-source honeypot frameworks.
Abstract
Public Large Language Model (LLM) APIs draw attacker traffic that defenders cannot see. Probes hit at the semantic layer—past TLS, past Web Application Firewall rules—and conventional intrusion detection picks up almost none of it. No open-source honeypot framework today captures this traffic at scale, and the few LLM-honeypot prototypes that exist push captured logs straight into a downstream LLM analyzer, exposing the analysis pipeline to indirect prompt injection through attacker-controlled inputs. We address both gaps with HIVE-AI, a 47,578-LoC honeypot framework deployed continuously on a single 4-vCPU/4-GB Virtual Private Server since 6 April 2026. Five protocol-faithful facades feed an eight-stage classification cascade with sub-5-ms p99 synchronous latency. The LLM threat-hunter is protected by a five-layer defense-in-depth architecture against indirect prompt injection, characterized theoretically and through operational field evidence; controlled per-layer validation is deferred to a follow-up deployment. We report these findings as a single-site, single-window case study: twenty days of operation captured 16,683 attacks from 1229 unique source IPs across 50 countries. The triangulation defense reduces mean adversarial evasion from 54.8 to 9.3% (paired test, p<0.001\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p<0.001$$\end{document}). Blind human validation on 100 events yields Cohen’s κ=0.74\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\kappa = 0.74$$\end{document} between the LLM and analyst majority—statistically indistinguishable from human-on-human κ=0.71\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\kappa = 0.71$$\end{document}. A local Ollama+Qwen2.5–1.5B backend reproduces the cloud severity verdict on 71% of events (κ=0.59\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\kappa = 0.59$$\end{document}, moderate agreement), a promising low-cost alternative rather than a full substitute. Code and dataset are released under MIT License and CC BY 4.0; the source code is archived at Zenodo HIVE-AI: A Honeypot Source Code (https://doi.org/10.5281/zenodo.19853664) and the live attack map at https://honeypot.ttpsec.cl:4443/livemap.
Ollure, a low- and medium-interaction honeypot that emulates the Ollama API without a backend LLM, is presented, providing empirical insight into real-world threats against exposed, self-hosted LLM services.
This work presents a systematic study of honeypot-aware budget allocation for LLM attack agents and shows that with the proposed detector-guided policy, LLM agent attackers can effectively allocate budget to compromise hosts in a host pool, highlighting the importance of dynamically allocating budget in a controlled mi...
Xin-Hong Xie, Piyush Nagasubramaniam, Neeraj Karamchandani et al.· 0 citations
GenPot is presented, a fine-tuned LLM-powered honeypot that integrates command-line, API, and dynamic web interaction to deliver realistic yet non-compromisable environments and is validated through a 14-day in-the-wild deployment and a human-in-the-loop credibility assessment.
Antonio Lara-Gutierrez, Juan Zamorano, J. A. Onieva· Applied intelligence (Boston...· 0 citations
We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for intelligence. Existing defenses embed traps inside model memory or rebuild d...
Integration of deterministic preprocessing with LLM-based reasoning enables the transformation of raw honeypot logs into structured and actionable cybersecurity intelligence, reducing analyst workload while improving the explainability and reliability of intrusion analysis in near-real-time environments.
Rúben Oliveira, Tiago Gomes, D. Pinho et al.· Journal of Cybersecurity and...· 0 citations
Large language models (LLMs) hosted on Microsoft Azure, primarily through Azure OpenAI Service, are increasingly embedded in enterprise applications that combine user input, retrieved documents, web content, and tool-calling agents within a single prompt context. This architectural pattern, while powerful, collapses th...
Shekar Rao Lakavath· Journal of Computer Science...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.