International Journal of Scientific Research and Engineering Development

Phishing attacks remain one of the most critical cybersecurity threats, where attackers create fraudulent websites to deceive users into revealing confidential information such as login credentials, financial data, and personal details. Traditional blacklist-based detection mechanisms fail to identify newly generated phishing URLs due to their dynamic and short-lived nature. This paper proposes a Web-Based Phishing Detection System using Machine Learning to classify URLs as legitimate or phishing in real time. The proposed framework extracts discriminative URL-based features including lexical characteristics, domain attributes, HTTPS usage, and suspicious patterns. Multiple machine learning classifiers such as Logistic Regression, Decision Tree, and Random Forest were trained and evaluated. Experimental results demonstrate that the Random Forest model achieves superior performance in terms of accuracy and generalization capability. The trained model is integrated into a web-based application for real-time prediction. The system enhances online security by reducing reliance on static blacklists and providing efficient detection of previously unseen phishing websites.

Ms.J.Jreeja, Mr.R.Lokeshwaran, Mr.K P Aakash, Ms.S.Vinothini, Mr.G.Ratheesh Kanna,"A Web Based Phishing Detection System Using Machine Learning" International Journal of Scientific Research and Engineering Development, V9(2): Page(1673-1677) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.