MAD-CTI: Cyber Threat Intelligence Analysis of the Dark Web Using a Multi-Agent Framework

The dark web is a host to illicit activities where hacker forums, blogs, and articles provide significant insights into Cyber Threat Intelligence (CTI) that are frequently unavailable on the surface web. The increasing incidence of security breaches underscores the necessity for advanced CTI solutio...

Full description

Saved in:
Bibliographic Details
Main Authors: Sayuj Shah, Vijay K. Madisetti
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10908603/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850250788311400448
author Sayuj Shah
Vijay K. Madisetti
author_facet Sayuj Shah
Vijay K. Madisetti
author_sort Sayuj Shah
collection DOAJ
description The dark web is a host to illicit activities where hacker forums, blogs, and articles provide significant insights into Cyber Threat Intelligence (CTI) that are frequently unavailable on the surface web. The increasing incidence of security breaches underscores the necessity for advanced CTI solutions to defend against emerging threats. This paper introduces MAD-CTI, a novel multi-agent framework based on Large Language Models (LLM) designed to extract insights from dark web sources. It independently scrapes, analyzes, and classifies content related to vulnerabilities, malware, and hacking, by leveraging a multi-agent architecture to improve efficiency, scalability, and consistency. By utilizing state-of-the-art LLM models and agents, we demonstrate how organizations can adopt this methodology to enhance the accuracy and efficiency of CTI.
format Article
id doaj-art-622c81dec5d44a2c9c2edac63895716d
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-622c81dec5d44a2c9c2edac63895716d2025-08-20T01:58:05ZengIEEEIEEE Access2169-35362025-01-0113401584016810.1109/ACCESS.2025.354717210908603MAD-CTI: Cyber Threat Intelligence Analysis of the Dark Web Using a Multi-Agent FrameworkSayuj Shah0Vijay K. Madisetti1https://orcid.org/0000-0002-6539-6769College of Computing, Georgia Institute of Technology, Atlanta, GA, USASchool of Cybersecurity and Privacy, Georgia Institute of Technology, Atlanta, GA, USAThe dark web is a host to illicit activities where hacker forums, blogs, and articles provide significant insights into Cyber Threat Intelligence (CTI) that are frequently unavailable on the surface web. The increasing incidence of security breaches underscores the necessity for advanced CTI solutions to defend against emerging threats. This paper introduces MAD-CTI, a novel multi-agent framework based on Large Language Models (LLM) designed to extract insights from dark web sources. It independently scrapes, analyzes, and classifies content related to vulnerabilities, malware, and hacking, by leveraging a multi-agent architecture to improve efficiency, scalability, and consistency. By utilizing state-of-the-art LLM models and agents, we demonstrate how organizations can adopt this methodology to enhance the accuracy and efficiency of CTI.https://ieeexplore.ieee.org/document/10908603/Cybersecurity defensecyber threat intelligencedark webhacklarge language models (LLMs)malware
spellingShingle Sayuj Shah
Vijay K. Madisetti
MAD-CTI: Cyber Threat Intelligence Analysis of the Dark Web Using a Multi-Agent Framework
IEEE Access
Cybersecurity defense
cyber threat intelligence
dark web
hack
large language models (LLMs)
malware
title MAD-CTI: Cyber Threat Intelligence Analysis of the Dark Web Using a Multi-Agent Framework
title_full MAD-CTI: Cyber Threat Intelligence Analysis of the Dark Web Using a Multi-Agent Framework
title_fullStr MAD-CTI: Cyber Threat Intelligence Analysis of the Dark Web Using a Multi-Agent Framework
title_full_unstemmed MAD-CTI: Cyber Threat Intelligence Analysis of the Dark Web Using a Multi-Agent Framework
title_short MAD-CTI: Cyber Threat Intelligence Analysis of the Dark Web Using a Multi-Agent Framework
title_sort mad cti cyber threat intelligence analysis of the dark web using a multi agent framework
topic Cybersecurity defense
cyber threat intelligence
dark web
hack
large language models (LLMs)
malware
url https://ieeexplore.ieee.org/document/10908603/
work_keys_str_mv AT sayujshah madcticyberthreatintelligenceanalysisofthedarkwebusingamultiagentframework
AT vijaykmadisetti madcticyberthreatintelligenceanalysisofthedarkwebusingamultiagentframework