Phishing URL Detection Using Naive Bayes Classification: A Robust Method for Accurate Detection

The proliferation of phishing attacks has posed significant threats to internet users and organizations, necessitating the development of efficient and accurate detection methods. This study presents a machine learning-based approach for detecting phishing URLs using the Naive Bayes classifier. The dataset, comprising various URL features such as entropy, domain age, and special character ratio, was preprocessed and trained using a Naive Bayes model. The model achieved a commendable accuracy rate of 85%, outperforming other classification algorithms such as Logistic Regression, Support Vector Machine (SVM), and Gradient Boosting. The results demonstrate that the Naive Bayes classifier, with its simplicity and computational efficiency, is effective for phishing URL detection, making it a viable solution for real-time implementation in cybersecurity applications. This research underscores the potential of probabilistic models in enhancing online security and reducing the impact of phishing threats.