Stack ensemble learning based phishing attacks detection system

Phishing is a cybercrime that aims to trap innocent web users with a fake website that visually resembles its real counterpart. Initially, users are directed to phishing websites through various social and technical redirection methods. Users who are unaware of the fakeness of the website may provide personal information such as user ID, password, credit card information, or bank account information to these sites. Phishing attackers use such information to commit serious crimes such as stealing money from banks, damaging the image of a brand, or even committing a crime. Although there are many phishing detection and prevention techniques in the existing literature, the emergence of intelligent machine learning and deep learning methods has expanded the scope of this field in the cybersecurity world. Therefore, there is a strong need to develop a system that efficiently detects phishing websites. While many studies use methods such as k nearest neighbor, logistic regression, random forest, support vector machines, decision trees, the stack ensemble learning method was proposed in this study. The stack ensemble learning based phishing detection method showed 96.6% accuracy.