Mitigating Phishing Threats: Cybersecurity Framework for Real-World Risk Reduction Using Machine Learning

Davis, Alias (2025) Mitigating Phishing Threats: Cybersecurity Framework for Real-World Risk Reduction Using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (842kB) | Preview
Preview	PDF (Configuration Manual) Download (462kB) | Preview

Abstract

Phishing attacks do continue to account for most of all reported data breaches, posing a critical threat to the global cybersecurity landscape. Despite the high precision Machine Learning-based detection systems have achieved in academic settings, their real-world impact is limited by a lack of integration with user awareness, live threat intelligence, organisational policies, and explainability. This study addresses such a gap since it designs and implements a practical multi-layer phishing defence framework which combines ensemble Machine Learning models with policy enforcement as well as simulated user training. The framework was developed with the use of open-source tools. Two publicly available phishing datasets validated that. The ensemble model's results reached 96.92% accuracy on the CSV dataset and 97.82% on the ARFF dataset, better than single models and simulated human participants, whose average accuracy was 78.5%. The framework is simple and understandable. It is also deployable upon standard hardware, along with mobile devices. The idea displays better security results now. This improvement occurs when detection is coupled with operational response. In actual practice, it gives to Small and Medium-sized Enterprises (SMEs). an accessible prototype. That prototype can be used by SMEs to reduce phishing risk. Even while the system cannot yet fully integrate into Security Information and Event Management (SIEM) or continually learn as it goes, its modular design still allows it future expansion. The study contributes with a reproducible multi-layered architecture for bridging detection precision to organisational defense.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hamdan, Mosab 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 H Social Sciences > HD Industries. Land use. Labor > Small Business Sector
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	17 Aug 2026 14:08
Last Modified:	17 Aug 2026 14:08
URI:	https://norma.ncirl.ie/id/eprint/9527

Actions (login required)

View Item