URL Detection using Gradient Boosting Classifier

The growing incidence of harmful URLs presents considerable threats to cybersecurity, making their identification an essential undertaking. This paper examines the use of Gradient Boosting Classifier (GBC) for detecting URLs, a machine learning approach recognized for its exceptional precision and resilience in classification tasks. The process involves extracting features from URLs, training the model, and assessing its performance using metrics like precision, recall, and F1-score. Findings indicate that GBC achieves a high level of accuracy in differentiating between safe and malicious URLs, surpassing conventional approaches. Future research will focus on improving the model with deep learning methods and expanding the dataset for wider applicability.