NORMA eResearch @NCI Library

Evaluating Machine Learning Models for Effective Phishing URL Detection

Mushayakarara, Reuel Tafara (2024) Evaluating Machine Learning Models for Effective Phishing URL Detection. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (817kB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (1MB) | Preview

Abstract

Phishing URL attacks deceive users into giving sensitive information by imitating legitimate URLs and this poses a cybersecurity threat. This research addresses the need for effective phishing URL detection by comparing various machine learning models. The focus is on determining which model among traditional (Logistic Regression), hybrid (Random Forest and Gradient Boosting Classifier) and advanced (Deep Neural Network) is most effective in detecting phishing URLs within a unified dataset. Another focus area is that of the impact of the feature extraction and selection to the performance of the models. Traditional models usually lack the capability to handle complex phishing URLs, while hybrid models offer better accuracy by combining multiple algorithms. Advanced models are complex to implement and need more computational resources. The study found that hybrid models had better accuracy and efficiency compared to other models. The practical implementation was through a web application that classifies a URL using the Random Forest model. The research further suggests enhancing the web application with user awareness training capabilities offering more effective and userfriendly phishing detection system.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Prior, Michael
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: 30 Jul 2025 13:20
Last Modified: 30 Jul 2025 13:20
URI: https://norma.ncirl.ie/id/eprint/8345

Actions (login required)

View Item View Item