Detection of Phishing URLs using Machine Learning - MSc Research Project - Cyber Security

Sep 17, 2026

Uploaded by Eliana

Phishing websites represent a growing cybersecurity risk by compromising sensitive customer and business data. Because phishing is the initial stage of many cyberattacks, prompt identification of such sites is critical. This MSc research project uses machine learning to strengthen detection beyond traditional manual feature engineering, which struggles against evolving tactics. URL-based features and multiple model training on a mixed dataset support an extensible system for phishing and zero-day identification, emphasizing incremental learning for near real-time updates using the PHIUSIIL and Mendeley datasets.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages22

Reading Time55 min

AccessFree to download

1 Introduction

1.1 Background

1.2 Research Question

1.3 Objectives

1.4 Contributions

Detection of Phishing URLs using Machine Learning MSc Research Project Cyber Security Emin Varghese Student ID: x23154250 School of Computing National College of Ireland Supervisor: Arghir Nicolae Moldovan National College of Ireland MSc Project Submission Sheet School of Computing Student Name: Emin Varghese Student ID: X23154250 Programme: MSc. Cybersecurity Year: 2024-25 Module: MSc. Research Project Supervisor: Arghir Nicolae Moldovan Submission Due Date: 12/12/2024 Project Title: Detection of Phishing URLs using Machine Learning Word Count: 6690 words excluding references Page Count: 20 I hereby certify that the information contained in this (my submission) is information pertaining to research I conducted for this project. All information other than my own contribution will be fully referenced and listed in the relevant bibliography section at the rear of the project. ALL internet material must be referenced in the bibliography section. Students are required to use the Referencing Standard specified in the report template. To use other author's written or electronic work is illegal (plagiarism) and may result in disciplinary action. Signature: Emin Varghese Date: 12/12/2024 PLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST | Attach a completed copy of this sheet to each project (including multiple copies) | □ | | --- | --- | | Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | □ | | You must ensure that you retain a HARD COPY of the project, both foryour own reference and in case a project is lost or mislaid. It is not sufficient to keep a copy on computer. | □ | Assignments that are submitted to the Programme Coordinator Office must be placed into the assignment box located outside the office. | Office Use Only | | | --- | --- | | Signature: | | | Date: | | | Penalty Applied (if applicable): | | Detection of Phishing URLs using Machine Learning Emin Varghese x23154250 Abstract Phishing websites are an increasing cybersecurity threat which puts both customers and business at risk as they compromise sensitive data. As phishing acts as the initial step in cyberattacks, early detection of these sites is important. Even though traditional methods, which rely on manual feature engineering are effective, they often find it difficult to catch up with the fishing tactics. This research emphasis on using machine learning (ML) to facilitate and enhance the detection process, improving its adaptability to rising threats. By reviewing URL-based features and training models on a mixed dataset, this study aims to make an innovative system that can easily identify phishing websites and zero-day attacks, improving the security measures and the decreasing the risks related to phishing attacks. PHIUSIIL and Mendeley datasets were preprocessed and then analyzed under six machine learning algorithms. The work also emphasizes the effectiveness of incremental learning solutions, especially for updating data in real-time. This work focuses on the application of machine learning (ML) for the detection of phishing URL. Using PHIUSIIL dataset and Mendeley dataset, a comparative analysis of URLs and content of different models was performed. The results prove the effectiveness of incremental learning strategies and bring focus on the need for strong and easily extendable methods adapted to the current threats. 1 Introduction 1.1 Background The digital evolution of the society driven by the accessibility and affordability of the internet which changed our engagement with essential services like banking, shopping, and education, meanwhile these advancements also opened the door to new vulnerabilities. The number of exploitations or cyber-attacks that occur on online platforms are increasing rapidly thereby compromising the sensitive or confidential data of groups or individuals. The phishing attack plays an i

FAQs

What is the main research focus of the project?

The project focuses on using machine learning to detect phishing URLs effectively, with attention to precision, scalability, and adaptability to real-time threats.

Why is early phishing URL detection important?

Phishing websites are an increasing threat because they enable cyberattacks that compromise sensitive personal or business data, making early detection essential for reducing risk.

What datasets and learning approach are emphasized?

The study preprocesses and analyzes the PHIUSIIL and Mendeley datasets and emphasizes incremental learning so the detection system can update data for real-time effectiveness.

Sep 17, 2026

Uploaded by Eliana