DEVELOPMENT OF A WEB BROWSER EXTENSION FOR PHISHING WEBSITE DETECTION USING MACHINE LEARNING - Dissertation Requirements

Aug 2, 2026

Upload by Sage

Development of a web browser extension for phishing website detection using machine learning focuses on building an end-to-end solution that collects and pre-processes web data, evaluates multiple machine learning models, and derives decision rules to support detection. The work applies exploratory data analysis, performs feature selection, and compares classifiers including decision tree, random forest, support vector classifier, logistic regression, and Gaussian naive Bayes. Results are validated with performance metrics, followed by browser extension implementation and discussion of detected phishing behavior and system handling.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Chapter One: Introduction

1.1 Background to the Study

1.2 Statement of the Problem

1.3 Aim and Objectives of the Study

1.4 Significance of the Study

Chapter Two: Literature Review

2.1 Preamble

2.2 Conceptual Review

2.3 Related Works

Chapter Three: Methodology

3.1 Preamble

3.2 Data Collection and Pre-processing

3.3 Evaluation of Multiple Models

3.4 Rule Extraction

3.5 Browser extension implementation

Chapter Four: Results and Discussion

4.1 Preamble

4.2 Data Collection

4.3 Evaluation Results

4.4 Rule Extraction

4.5 Phishing Detection Web-based Platform

4.6 Discussion of Findings

DEVELOPMENT OF A WEB BROWSER EXTENSION FOR PHISHING WEBSITE DETECTION USING MACHINE LEARNING DUROJAIYE, PEACE DUROJAIYE (15CH03729) B.Sc. Management Information system, Covenant University, Ogun state AUGUST, 2023 DEVELOPMENT OF A WEB BROWSER EXTENSION FOR PHISHING WEBSITE DETECTION USING MACHINE LEARNING BY DUROJAIYE, PEACE DUROJAIYE (15CH03729) B.Sc. Management Information system, Covenant University, Ogun state A DISSERTATION SUBMITTED TO THE SCHOOL OF POSTGRADUATE STUDIES IN PARTIAL FULFILMENT OF THE REQUIREMENTS FOR THE AWARD OF MASTER OF SCIENCE (M.Sc) DEGREE IN MANAGEMENT INFORMATION SYSTEMS IN THE DEPARTMENT OF COMPUTER AND INFORMATION SCIENCES, COLLEGE OF SCIENCE AND TECHNOLOGY, COVENANT UNIVERSITY, OTA, OGUN STATE, NIGERIA AUGUST, 2023 ACCEPTANCE This is to attest that this dissertation is accepted in partial fulfilment of the requirements for the award of the degree of Master of Science in Management Information System in the Department of Computer and Information Sciences, College of Science and Technology, Covenant University, Ota, Nigeria. Miss Adefunke F. Oyinloye (Secretary, School of Postgraduate Studies) Signature and Date Prof. Akan B. Williams (Dean, School of Postgraduate Studies) Signature and Date DECLARATION I, DUROJAIYE, PEACE OLUWASEYI (15CH03729), declare that this research was carried out by me under the supervision of Dr. Aderonke A. Oni of the Department of Computer and Information Sciences, College of Science and Technology, Covenant University, Ota, Ogun State, Nigeria. I attest that the dissertation has not been presented either wholly or partially for the award of any degree elsewhere. All sources of data and scholarly information used in this dissertation are duly acknowledged. DUROJAIYE, PEACE OLUWASEYI Signature and Date CERTIFICATION We certify that this dissertation titled “DEVELOPMENT OF A WEB BROWSER EXTENSION FOR PHISHING WEBSITE DETECTION USING MACHINE LEARNING” is an original research work carried out by DUROJAIYE, PEACE OLUWASEYI (15CH03729) in the Department of Computer and Information Sciences, College of Science and Technology, Covenant University, Ota, Ogun State, Nigeria under the supervision of Dr. Aderonke A. Oni. We have examined and found this work acceptable as part of the requirements for the award of Master of Science (M.Sc.) in Management Information System. Dr. Aderonke A. Oni (Supervisor) Signature and Date Prof. Olufunke O. Oladipupo (Head of Department) Signature and Date Prof. Olufunke O. Vincent (External Examiner) Signature and Date Prof. Akan B. Williams (Dean, School of Postgraduate Studies) Signature and Date DEDICATION This dissertation is dedicated to God, who is my source of strength, wisdom, inspiration and knowledge. My heartfelt gratitude goes to my parents, Pastor and Pastor (Mrs.) B.ADurojaiye and siblings; Victor, Joy, my twin brother (John) and Victoria for their unending support and encouragement in diverse ways possible. To my colleagues (Favour, Dami, Ope, Emma, Jumoke, Faith and Paul) and loved ones who have been instrumental in their way towards fulfilling this quest, I appreciate you all and may God bless you all abundantly. ACKNOWLEDGEMENTS First, I want to acknowledge God Almighty for his mercy and strength that enabled me to carry out this research study efficiently and effectively. I want to specially thank my parents and siblings for all their love and support. Secondly, I want to specially thank my supervisor Dr. Aderonke A. Oni for her effort in making sure this research study was a success and also her guidance and patience and the understanding she impacted unto me, thank you so much ma, May God Almighty continue to bless and protect you. Thirdly, I want to thank and give my regards to the Management and Chancellor of Covenant University for the calm and adventurous environment that has enabled me to pursue my dreams and passion in academics. I also want to appre

FAQs

What problem does the dissertation address?

The dissertation addresses phishing website detection, aiming to identify deceptive phishing sites through machine learning rather than relying only on manual or static defenses.

How is the solution designed and implemented?

The approach includes data collection and pre-processing, exploratory data analysis, feature selection, evaluation of multiple models, and rule extraction, followed by implementation of a browser extension that displays alerts and results.

Which machine learning models are evaluated?

The study evaluates decision tree, random forest, support vector classifier (SVC), logistic regression, and Gaussian naive Bayes, and compares their performance using defined metrics.

Aug 2, 2026

Upload by Sage