Threat Intelligence-Driven Machine Learning Framework for Predictive Ransomware Detection

Raju, Ranjitha (2025) Threat Intelligence-Driven Machine Learning Framework for Predictive Ransomware Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (754kB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

Ransomware poses an escalating threat to digital infrastructures, leveraging stealth and rapid propagation to bypass conventional detection systems. This research introduces a predictive machine learning framework driven by threat intelligence, aimed at early detection of ransomware activity using enriched network telemetry. By correlating structured network flow data with live Indicators of Compromise (IOCs) sourced from verified threat feeds such as Medusa, the system dynamically adapts to evolving attack patterns. Using the CTU-13 dataset as a baseline and integrating threat-enriched features, the proposed approach employs advanced supervised models particularly XGBoost and Random Forest to identify malicious behavior. Experimental results demonstrate strong predictive performance, with XGBoost achieving a precision of 0.91, recall of 0.89, and F1-score of 0.90, outperforming baseline models. Furthermore, SHAP-based explainability was integrated to provide transparency in decision-making, enhancing trust in operational deployment. This framework moves beyond static rule-based detection by offering a modular, interpretable, and real-time compatible solution. It represents a practical step forward in threat-aware, proactive ransomware defense strategies for enterprise environments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Vikas UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	16 Jun 2026 14:24
Last Modified:	16 Jun 2026 14:24
URI:	https://norma.ncirl.ie/id/eprint/9370

Actions (login required)

View Item