Phishing Classifier For Websites

The book involves the development of a web-based application that integrates multiple machine learning models-including XGBoost Logistic Regression and Gaussian Naive Bayes-to classify URLs as either phishing or legitimate. The models were trained using real world datasets consisting of over 5000 phishing URLs and 5000 legitimate ones collected from trusted sources like Phish Tank and the University of New Brunswick. Key steps in the system include data preprocessing feature selection and feature extraction focusing on elements like URL structure domain age and embedded scripts. The system leverages exploratory data analysis to visualize data insights and employs Principal Component Analysis (PCA) to optimize the model by reducing redundant data.