WEB PHISHING DETECTION SYSTEM USING MACHINE LEARNING

Phishing attacks are one of the most common cybersecurity threats, targeting users by creating fraudulent websites that mimic legitimate platforms to steal sensitive information such as login credentials and financial data. Traditional detection methods rely on blacklists and rule-based systems, which are often ineffective against newly generated phishing websites. This project proposes a machine learning-based web phishing detection system that can identify malicious websites in real time. The objective of the system is to improve detection accuracy and reduce reliance on static rules by learning patterns from website features. The methodology involves extracting features such as URL structure, domain information, and webpage content, followed by training classification algorithms to distinguish between legitimate and phishing websites. The system uses supervised learning techniques, including algorithms like Decision Tree and Random Forest, to classify websites based on extracted features. The results demonstrate high detection accuracy, reduced false positives, and improved capability to detect previously unseen phishing attacks. The proposed system provides an efficient, scalable, and automated solution for enhancing web security and protecting users from phishing threats.