A Comparative Analysis of Detection Methods for Phishing Websites Using Machine Learning
Samuel-Soma M. Ajibade, Muhammed Basheer Jasser, David Olayemi Alebiosu, Bayan Issa, Lee Wei San, Ghassan Saleh ALDharhani · 2025
Phishing websites pose a significant cybersecurity threat by exploiting user trust and mimicking legitimate online platforms to steal sensitive information such as usernames, passwords, and financial data. This study leverages machine learning algorithms such as Random Forest, Logistic Regression, and K-Nearest Neighbors (KNN) to address this issue by analyzing key website features, identifying patterns linked to phishing activity, and evaluating algorithm performance using standard metrics like accuracy, precision, recall, and F1-score. The results indicate that Random Forest outperforms the other methods in terms of accuracy and robustness, while Logistic Regression offers interpretability and efficiency, and KNN demonstrates flexibility despite computational limitations. These findings highlight the effectiveness of machine learning in detecting phishing websites and provide insights for developing scalable cybersecurity solutions.