Enhancing Phishing URL Detection by Leveraging Machine Learning and Deep Learning Models

Chinthalapalli, Charan Deep (2024) Enhancing Phishing URL Detection by Leveraging Machine Learning and Deep Learning Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (367kB) | Preview

Abstract

Phishing is one of the most popular types of cybercrime; it deceives the users to surrender some personal information through the help of fake sites that mimic the real ones. Phishing URLs are difficult to detect and are currently one of the biggest issues because of the growing complexity of these attacks and the inefficiency of the measures. This paper aims to compare the efficiency of multiple machine learning and deep learning techniques for the detection of phishing URLs with an emphasis on the impact of feature engineering. The work compares several machine learning models such as Random Forest, AdaBoost, Logistic Regression, LSTM, and TabNet using a labeled set of URLs comprising benign and phishing URLs. To enhance the classification performance, a few properties like the URL length, special characters in the URL, the use of the HTTPS protocol, and several subdomains are extracted. The research evaluates model performance based on the evaluation parameters including accuracy, precision, recall, and F1-score, and addresses issues like class imbalance and dataset complexity. The results reveal that the model with the highest accuracy was XGBoost with 88.93%, while deep learning models such as LSTM and TabNet were slightly lower. However, Random Forest and XGBoost enhance the performance in detecting phishing URLs, and the traditional machine learning methodologies are sufficient for detecting phishing URLs.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Pantridge, 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:	18 Jul 2025 10:26
Last Modified:	18 Jul 2025 10:26
URI:	https://norma.ncirl.ie/id/eprint/8195

Actions (login required)

View Item