<![CDATA[Phishing attacks represent a significant cybersecurity threat aimed at stealing sensitive user information through psychological manipulation using fake websites. Conventional detection methods relying on blacklists are considered ineffective in recognizing zero-day attacks or newly published phishing sites. This study aims to develop an automated detection model using a Machine Learning approach by comparing the performance of two Supervised Learning algorithms: K-Nearest Neighbor (K-NN) and Decision Tree. The dataset used is sourced from the UCI Machine Learning Repository, consisting of 11,055 records with 30 URL characteristic features. Performance evaluation was conducted using Accuracy metrics and Confusion Matrix analysis. Experimental results indicate that the Decision Tree algorithm significantly outperforms K-NN with an accuracy of 95.21%, while K-NN achieved an accuracy of only 60.11%. Furthermore, Decision Tree demonstrated a very low False Negative rate, making it a more recommended model for real-time cybersecurity system implementation.]]>
Copyrights © 2026
