AI-Powered Phishing Detection: Overcoming Gaussian RBF Kernel Limitations

Narayan, Vatsala (2025) AI-Powered Phishing Detection: Overcoming Gaussian RBF Kernel Limitations. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Phishing attacks are one of the most persistent and critical threats in cybersecurity, affecting nearly 86% of the organizations as seen in the statistics. They exploit vulnerabilities by imitating legitimate sources and trick the users into revealing sensitive and personal information. Nearly 90% of cybersecurity breaches are highly done by taking advantage of human vulnerability. This thesis thus helps us investigate by comparing multiple machine learning methods for dynamic detection of phishing Uniform Resource Locator (URLs). It includes the traditional Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and a hybrid CNN-RNN model. The objective here is to evaluate and compare the performance of these models against the attributes such as the accuracy, generalization, and real-time deployment feasibility. All the models are trained in highly curated phishing datasets which are assessed using metrics that are used for standard classification. A real-time prototype is also built to demonstrate the prediction of the best performing and machine learning models and their feasibility. The research focuses to highlight the importance of deep learning in this complex and targeted method of phishing threats to provide deep insight on how to select one of the most effective architectures for the security of real-world applications that will save the organizations to deal with real time phishing attacks.

Item Type:	Thesis (Masters)
Supervisors:	Name Email McCabe, Liam UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence 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:	16 Jun 2026 13:47
Last Modified:	16 Jun 2026 13:47
URI:	https://norma.ncirl.ie/id/eprint/9364

Actions (login required)

View Item