Malware Detection with Supervised Algorithms: Identifying Malicious Links with Browser Extensions

This research project aims to develop a user-friendly browser extension that identifies and warns users about dangerous URLs hosting downloadable file content using Supervised machine learning methods. Models like Deep Neural Networks (DNN), Support Vector Machines (SVM), Decision Trees, XGBoost, and Random Forests were used to ensure high precision and dependability. This approach starts with careful data preparation, which includes loading, cleaning, and standardizing a dataset of URLs. Features were chosen and the Datasets were divided into training and testing for the models. These models were trained to spot malicious URLs using popular libraries such as TensorFlow and Scikit- Learn. A Chrome extension was developed to keep an eye on URLs as you browse and communicate with the backend Flask API to determine if they're safe. These tests show the system does a good job telling safe and dangerous URLs apart from warning users. This project aims to make the internet safer by using Browser Extensions with machine learning models for malware detection to create a handy and safe tool for everyday web surfers, and it contributes to the advancement of cybersecurity tools, offering a practical solution for enhancing web security against evolving threats.