Strengthening Proactive Cyber Defence: Innovative Approaches for Effective Cyber Threat Intelligence Gathering, Analysis and Application

Ramasamy, Chandhiya (2023) Strengthening Proactive Cyber Defence: Innovative Approaches for Effective Cyber Threat Intelligence Gathering, Analysis and Application. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (798kB) | Preview
Preview	PDF (Configuration Manual) Download (856kB) | Preview

Abstract

In response to the escalating threat of data poisoning assaults on machine learning-based security systems in cyber threat intelligence (CTI), this research introduces an innovative methodology. Leveraging the algorithms Isolation Forest, Logistic Regression, and Support Vector Machines (SVM), the study addresses the critical need to enhance system resilience. Through experimentation with a synthetic CTI Common Vulnerabilities and Exposures (CVE) dataset, feature selection, and rigorous model training, the study observed that Logistic Regression and Support Vector Machines (SVM) outperformed Isolation Forest. The comparative analysis of different models revealed distinct performance metrics, identifying Logistic Regression and SVM as particularly adept in identifying data poisoning threats and demonstrating resilience across a variety of conditions. The study's theoretical contribution lies in advancing anomaly detection within CTI datasets, aligning with the current state of the art while introducing a novel combination of established techniques. In practice, this research fortifies machine learning-based security mechanisms, providing tangible protection against data tampering and enhancing the reliability of CTI outputs. Remaining unresolved aspects offer avenues for future work, emphasizing hyperparameter optimization, exploring additional anomaly detection techniques, and practical deployment scenarios. These opportunities signify potential refinement and extension of the proposed methodology in the dynamic landscape of cyber threat intelligence.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Salahuddin, Jawad 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 > Algebra > Algorithms > Computer algorithms 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:	22 Apr 2025 12:40
Last Modified:	22 Apr 2025 12:40
URI:	https://norma.ncirl.ie/id/eprint/7457

Actions (login required)

View Item