DUROJAIYE, PEACE DUROJAIYE and Covenant University, Theses (2023) DEVELOPMENT OF A WEB BROWSER EXTENSION FOR PHISHING WEBSITE DETECTION USING MACHINE LEARNING. Masters thesis, COVENANT UNIVERSITY.
![[img]](http://eprints.covenantuniversity.edu.ng/style/images/fileicons/application_pdf.png) |
PDF
Download (226kB) |
Abstract
Online platforms play a critical role in daily life; however, they expose users to cybersecurity threats, including phishing attacks. This study focuses on developing a web browser extension that utilizes machine learning techniques to identify phishing websites with enhanced accuracy. Five machine learning algorithms - Decision Tree, Random Forest, Support Vector Machine (SVM), Logistic Regression, and Gaussian Naive Bayes - were evaluated for phishing detection using a dataset of 11,430 URLs consisting of 87 features such as URL length, domain age, and web traffic. The study also engaged Exploratory Data Analysis to extract key insights from the dataset. The evaluation reveals the effectiveness of different machine learning models. Metrics like accuracy, precision, recall, and F1 score are provided for each model, highlighting their strengths and limitations. Through cross-validation and careful hyperparameter tuning, the Random model emerges as the most accurate. Rule extraction is then applied to this model, yielding understandable rules that illuminate its decision-making process. Additionally, the study practically applies the developed model through a phishing detection Web Browser Extension. This extension offers real-time website validation and alerts users about potential phishing risks. By seamlessly integrating machine learning into a user-friendly interface, the browser extension empowers users to assess website legitimacy, thereby enhancing online security. This study offers valuable insights into cybersecurity by presenting an efficient machine learning method for the identification and classification of phishing websites. The findings underscore the potential of this model to safeguard sensitive information and counter the rising threat of phishing attacks.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Phishing detection, machine learning, Web-based Platform, real-time detection, cybersecurity, browser extension. |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science |
| Depositing User: | AKINWUMI |
| Date Deposited: | 03 Oct 2023 13:19 |
| Last Modified: | 03 Oct 2023 13:19 |
| URI: | http://eprints.covenantuniversity.edu.ng/id/eprint/17336 |
Actions (login required)
 |
View Item |
