Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198044,
        author = {PARSA ARUNKUMAR and Dr.K.B.Sathya and Nomula Srinivas and Palagani Naveen and Nigidala Manikanta},
        title = {Multi Agent framework for Cyber threat intelligence Analysis of dark web},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {7884-7893},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198044},
        abstract = {The rapid growth of cybercrime on the dark web poses significant challenges for organizations seeking to protect sensitive data and maintain cybersecurity resilience. Traditional manual monitoring approaches are often insufficient due to the sheer volume, diversity, and dynamic nature of dark web content. This paper presents a multi-agent framework for cyber threat intelligence (CTI) analysis, integrating autonomous agents with machine learning techniques to efficiently collect, preprocess, and analyze dark web data. The system is designed to detect and classify emerging threats, enabling proactive risk mitigation. The proposed framework employs agents to gather information from various dark web sources, including forums, marketplaces, and chat platforms, while maintaining anonymity and operational scalability. Preprocessed data is transformed into feature vectors capturing threat-related patterns, which are then analyzed using machine learning classifiers to categorize threats such as malware distribution, phishing campaigns, and ransomware activities. The framework also prioritizes threats based on severity and potential impact, providing actionable intelligence to security analysts through interactive dashboards and automated reports.Experimental results demonstrate that the system achieves high accuracy, precision, and recall in threat classification, even in the presence of noisy and unstructured data. Comparative analysis with existing models highlights the framework’s balance between computational efficiency and detection performance, making it suitable for real-time monitoring and operational deployment. Overall, the proposed system offers a scalable, intelligent, and automated solution for dark web CTI, empowering organizations to proactively anticipate and respond to cyber threats.},
        keywords = {Cyber Threat Intelligence, Dark Web Analysis, Multi-Agent System, Machine Learning, Threat Detection, Automated Monitoring, Data Preprocessing, Threat Classification, Real-Time Cybersecurity, Dark Web Crawling.},
        month = {April},
        }