AMADI, CHIBUIKEM FRANCIS (2026) DEVELOPMENT OF A REAL-TIME PHISHING WEBSITE DETECTION SYSTEM. Other thesis, Godfrey Okoye University, Enugu Nigeria.
![[img]](https://eprints.gouni.edu.ng/style/images/fileicons/text.png) |
Text
AMADI PROJECT WORK COMPLETE.pdf Download (1MB) |
Abstract
Phishing has emerged as a massively common type of cyber threat, relying on misleading websites and emails to obtain confidential user information. Most traditional phishing detection techniques such as blacklists and rules-based detectors have trouble keeping pace with new and emerging threats in real-time. In this paper we describe the design and development of a machine learning-based, real-time phishing detection system (RTS) that greatly enhances both the accuracy and speed of detecting phishing attacks. The RTS detects phishing through a random forest classification model trained on datasets of email messages and URLs marked as either phishing or legitimate. Features related to phishing were extracted from the input URLs and email messages through a feature extraction module, and the input URLs were geolocated through an embedded geolocation module to provide additional geographic intelligence of the originating domain/email sender. The RTS was implemented as a web-based application developed using Python, Flask (Web Application Framework), HTML, CSS and JavaScript, thereby providing a user-friendly interactive interface for users to conduct real-time phishing attacks. Evaluating the RTS using standard machine learning metrics, the RTS achieved a 97% accuracy rate, 95% precision, 97% recall, and 96% F1-Scores. These evaluation results demonstrate that the RTS is a viable solution to detect phishing attacks and to provide additional context to the detected threat from the geolocation analysis. The study concludes that integrating machine learning with real-time web technologies offers a practical and reliable solution for mitigating phishing attacks.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | Q Science > Q Science (General) |
| Divisions: | Faculty of Computing And Information Technology (FACIT) |
| Depositing User: | Cynthia Ugwuoti |
| Date Deposited: | 30 Jul 2026 12:08 |
| Last Modified: | 30 Jul 2026 12:08 |
| URI: | http://eprints.gouni.edu.ng/id/eprint/6086 |
Actions (login required)
 |
View Item |
