Malicious URL Detection using Machine Learning

Project Overview

With the rise of phishing, malware, and cyber-attacks, malicious URLs have become a major threat in cybersecurity. This project focuses on building a machine learning model that can classify whether a given URL is safe or malicious, based on patterns and extracted features.

We use techniques to analyze URL. Machine Learning features are then used to train classification models such as Random Forest, SVM, XGBoost, or LightGBM to accurately detect potential threats.

This project can be applied to browser security, email filters, and anti-virus systems, making it a practical real-world cybersecurity solution.

Tools & Technologies Used

Loading Datasets.
Data Preprocessing.
Counting Different Types Of URLs.
EDA and Visualizing Numerical Columns
Correlation.
Creating and Comparing Machine learning models : Decision Tree , Random Forest, Logistic Regression, Ada Boost, LGBM, ANN.
Saving The Models and Finding Users Predictions.