Phishing URL Detection Using Machine Learning

Abstract

Phishing attacks pose a significant threat in the digital landscape, requiring effective detection of phishing URLs. This paper explores machine learning techniques for phishing URL detection, including feature extraction and model training using algorithms such as Logistic Regression, Random Forest Classifier, Decision Tree, Support Vector Classifier, K-Neighbors Classifier, and MLP Classifier. The models were evaluated using labeled datasets and achieved promising accuracy, with the Random Forest Classifier performing best. Deployment of these models in real-time systems enhances protection against phishing attacks. Continuous monitoring, feedback collection, and model improvement contribute to staying ahead of emerging threats. By combining machine learning with other cybersecurity measures, users can safeguard their sensitive information.