Leveraging Large Language Models (LLM) for the Detection of Spear-Phishing Emails as Indicators of Advanced Persistent Threats (APTs)

Abdul Azeez, Aslam Malik (2024) Leveraging Large Language Models (LLM) for the Detection of Spear-Phishing Emails as Indicators of Advanced Persistent Threats (APTs). Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (601kB) | Preview
Preview	PDF (Configuration Manual) Download (260kB) | Preview

Abstract

Spear phishing and Advanced Persistent Threats (APTs) are targeted and context-specific, they escape detection by traditional systems (Xuan, 2021). In this research, an advanced detection framework is developed using state-of-the-art machine learning (ML) techniques. The system extracts feature from the content of email and (Innab et al., 2024) email header and social behaviour data to identify language anomalies, metadata patterns and user activity profiles indicative of threats.

The framework reaches high accuracy, precision, recall, F1 scores using ML models such as deep learning and supervised learning, surpassing traditional systems. More specifically this work focuses on the utilization of ML methods to mitigate cybersecurity risks and adds to the burgeoning field of intelligent threat detection systems (Innab et al., 2024) which pinpoints the importance of data in improving organizational security. However even more work needs to be done, but this approach is a promising step forward to counter cyber threats.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Khan, Imran UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing 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:	18 Jul 2025 08:51
Last Modified:	18 Jul 2025 08:51
URI:	https://norma.ncirl.ie/id/eprint/8182

Actions (login required)

View Item