Evaluating the Effectiveness of Machine Learning Algorithms in Detecting Phishing Attacks

Praturi, Sunil Kumar (2024) Evaluating the Effectiveness of Machine Learning Algorithms in Detecting Phishing Attacks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (477kB) | Preview
Preview	PDF (Configuration Manual) Download (496kB) | Preview

Abstract

Phishing continues to be one of the most frequent and dangerous types of cyber attacks that result in liquidated funds and leakage of information. This paper describes the design and assessment of a machine-learning algorithm for the detection of phishing URLs. The objective of the study was to learn and categorise phishing websites with the help of machine learning algorithms such as Random Forest classifier, SVM classifier, k-NN classifier, Na¨ıve Bayes classifier and Decision Tree classifier. The study comprised an open-source dataset of features, including the length of the URL, similarity of domains, and previous response records, among others. This work shows the effectiveness of Random Forest and SVM with a precision of 0.9814, F1-Scores 0.9705, Specificity: 0.99 and Accuracy of 0.9974 and ROC-AUC value of more than 0.99. The study also shows how feature selection and hyperparameters should be carefully conducted in order to achieve the best outcome. Furthermore, the study presents a discussion of these results for theoretical and empirical research and practical applications in cybersecurity. Despite high Accuracy in standard datasets in challenged scenarios, the static models fail in dealing with imbalanced datasets and cannot incorporate the more numerous, but irrelevant indicators. In conclusion the authors provide suggestions for potential future work based on the idea of introducing other deep learning methods in order to enhance and improve the result of the real-time testing of the presented models.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Heffernan, Niall 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:	28 Jul 2025 09:14
Last Modified:	28 Jul 2025 09:14
URI:	https://norma.ncirl.ie/id/eprint/8243

Actions (login required)

View Item