Unveiling the Power of CNNs with Attention for URL Phishing Detection

Shukla, Tanmay Dharmaraj (2024) Unveiling the Power of CNNs with Attention for URL Phishing Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (4MB) | Preview

Abstract

91% of cybercrimes is initiated using phishing emails where the victim's personal sensitive information is achieved by the attacker.URL poses prime threats to online security which leads to financial losses and privacy which motivates us to investigate and propose a robust solution. This study is conducted to investigate URL phishing detection methods that traditional methods didn’t achieve and focuses on the comparison between machine learning and deep learning approaches. This study will explore the effectiveness of both ML and DL models using datasets containing benign and phishing URLs sourced from online repositories. The dataset has been split into training and testing stages in a ratio of 90:10 which is applied to 3 models. Random Forest Classifier and Extra Tree Classifier form Machine learning models, alongside Deep learning models such as Convolutional Neural Network with Attention Mechanism were implemented. Performance evaluation was done with the help of a confusion matrix and classification report. Further, an application using Flask is developed for testing phishing URLs. This web application will show URL phishing detection systems which will identify whether the entered URL is phishing or safe. Lastly, it was observed that CNN model performs best with superior and good accuracy of 91%.

Item Type:	Thesis (Masters)
Supervisors:	Name Email McLaughlin, Eugene 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:	05 Jun 2025 11:00
Last Modified:	05 Jun 2025 11:00
URI:	https://norma.ncirl.ie/id/eprint/7752

Actions (login required)

View Item