URL Based Phishing Website Detection by Using Gradient and Catboost Algorithms

Abstract

Abstract: Phishing is one of the most common and most dangerous attacks among cybercrimes. The aim of these attacks is to steal the information used by individuals and organizations to conduct transactions. Phishing websites contain various hints among their contents and web browser-based information. In existing system the Random forest algorithm is used. In our proposed system, we are using different classification algorithm like bagging and boosting algorithms that are Gradient Boosting, Cat boosting to increase accuracy. The features extracted based on the features of websites in UC Irvine Machine Learning Repository. Here, we have performed the performance analysis between the boosting algorithms like Gradient boost, Cat boost and the random forest. From the performance analysis we can determine the best suitable algorithm to detect the phishing website .This study is considered to be an applicable design in automated systems with high performing classification against the phishing activity of websites.