About This Project
This research project focuses on training machine learning models and deep neural networks to predict phishing websites, a critical aspect of cybersecurity. Phishing attacks remain one of the most prevalent threats to online security.
The dataset was created by gathering both phishing and benign URLs of websites. From these URLs, required URL and website content-based features were extracted to train the models. This comprehensive approach ensures robust detection capabilities.
Multiple machine learning algorithms were compared including Logistic Regression, Support Vector Machine (SVM), Decision Tree, Random Forest, and XGBoost Classifier. The comparative study helps identify the most effective approach for phishing detection.