Phishing URL Detection Using XGBoost

Abstract

Abstract: Phishing attacks are a major threat to cybersecurity, affecting individuals and organizations around the world. In this project we are developing a phishing site detection system using XGBoost, a widely used machine learning algorithm that is well-known for its effectiveness and precision in classification tasks. Our approach involves extracting features from URLs and related domains, preprocessing that data, and training XGBoost’s model. We test our system’s performance by using a dataset of both phishing and normal websites to see how well our system detects phishing attempts. The approach involves the extraction of features from URLs and associated domains, followed by data preprocessing and the training of XGBoost’s model. Performance evaluation is conducted using a dataset comprising both phishing and legitimate websites to assess the system’s efficacy in detecting phishing attempts. The project aims to enhance cybersecurity measures by providing an efficient and accurate solution for identifying and mitigating phishing attacks, ultimately contributing to the protection of online users and organizations against malicious activities