The purpose of this poject is to use the structural features of the URL to detect malicious URLs using supervised, unsupervised algorithms of machine learning and multi-layer neural network in deep learning. So our goal is to evaluate the performance of different machine learning algorethms to detect malicious URLs, using a set of tagged URL data, which are presented here https://www.kaggle.com/code/siddharthkumar25/detect-malicious-url-using-ml/data. We test different algorithms and models to identify the most relevant features for detecting malicious URLs, and to compare the performance of different techniques.
You will find here the hall code commented and the rapport well explained.