Malicious URL Detection Using Random Forest

Phishing remains a significant threat to online security, with attackers continuously evolving their tactics to deceive unsuspecting users. Traditional detection methods often fall short in identifying these sophisticated phishing attempts. In our research, we developed an effective phishing URL detection system using a Random Forest classifier. We analyzed a dataset of 11,000 URLs, both phishing and legitimate, extracting 31 features related to URL structure, domain authority, and webpage content. Our method included careful data preprocessing, feature extraction, and fine-tuning of the model’s parameters. The result was a highly accurate model, achieving $99.0 \%$ accuracy on training data and $96.9 \%$ on test data. These impressive results highlight the strength of the Random Forest approach in spotting phishing URLs and offer a scalable solution for real-time protection. To make this tool accessible, we have deployed it on a web page, allowing users to easily check links for potential threats and improve their online safety.