Insider Threat Detection using Ensemble and Sequential Models

Joy, Arun (2024) Insider Threat Detection using Ensemble and Sequential Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (613kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Insider threats are the major cybersecurity risks to the organisations that causing damage. Current detection approaches rely on predetermined criteria struggle to recognise small behavioural deviations. This insider problem research approaches by analysing behavioural patterns and anomalies within the user activity data. In order to solve this problem, this research used the CERT Insider Threat dataset and sophisticated machine learning algorithms to find unusual email communication patterns. This study used advanced algorithms like Random Forest, Isolation Forest, LSTM, GRU and Stacking Ensembles with feature engineering techniques including time-based and textual evaluation. The comparative study demonstrated that ensemble learning approaches, particularly the Stacking Classifier, significantly increased the detection accuracy when compared to traditional methods. These findings support the body of research on machine learning's effectiveness in anomaly detection and highlight the value of hybrid models in enhancing insider threat identification. In practice, this method gives the businesses a strong foundation for anticipating and proactively identifying hazards.

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:	23 Jul 2025 14:09
Last Modified:	23 Jul 2025 14:09
URI:	https://norma.ncirl.ie/id/eprint/8217

Actions (login required)

View Item