Paper Title
An Effective Machine Learning Framework for Phishing Website Detection Using Gradient Boosting and Web Application Deployment via Flask

Abstract
Phishing attacks have emerged as a significant cyber security threat, targeting users through deceptive websites that mimic legitimate services to steal sensitive information. As traditional rule-based systems struggle to keep pace with evolving attack vectors, machine learning has proven to be a powerful alternative for detecting and mitigating such threats. This study proposes a machine learning-based phishing detection system that leverages key URL features to distinguish between legitimate and malicious websites. The approach involves rigorous feature engineering, classification model training, and system deployment within a lightweight, scalable architecture. Various supervised learning algorithms are explored to identify the most effective classifiers for this task. The finalized detection model is integrated into a Flask-based web application, enabling real-time URL verification through an intuitive interface. This deployment enhances accessibility and ensures rapid, user-friendly threat detection. The proposed system contributes to the growing body of research on intelligent cyber security solutions and offers a practical tool to empower individuals and organizations in safeguarding digital interactions. By combining machine learning with a deployable web interface, this work bridges the gap between theoretical threat detection models and real-world user protection, marking a step forward in proactive cyber security defense. Keywords - Phishing Detection• Machine Learning• URL Analysis• Web Security• Cyber security• Prediction