A Novel Approach for Detecting Insider Threats by Combining Behavioural Analytics and Threat Intelligence

Umunna, Fumnanya Omoniyi (2024) A Novel Approach for Detecting Insider Threats by Combining Behavioural Analytics and Threat Intelligence. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (507kB) | Preview
Preview	PDF (Configuration Manual) Download (521kB) | Preview

Abstract

With insider threats posing a formidable risk due to the privileged access and knowledge of organizational infrastructure, traditional security measures often fail to detect such anomalies. The research objectives focus on applying the Isolation Forest Model for anomaly detection, assessing system logs to uncover insider threats, and detecting inconsistencies in user activities. The primary research question investigates the integration of behavioural analytics with threat intelligence to improve insider threat detection within corporate environments. The methodologies adopted address the dynamic nature of these threats by utilizing machine learning and behavioural analytics to discern anomalies in user behaviour. The application of deep learning approaches, specifically the Deep Isolation Forest methodology, demonstrates significant advancements in this field. The solution entailed a systematic approach, utilizing anomaly scores to flag potential insider threats. Visualizations of user-PC interactions, file transfer frequencies, and logon/logoff activities were generated, highlighting users with irregular behaviours. An integrated threat assessment combined these varied data points to provide a comprehensive risk analysis.

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:	03 Jun 2025 17:14
Last Modified:	03 Jun 2025 17:14
URI:	https://norma.ncirl.ie/id/eprint/7740

Actions (login required)

View Item