A Novel Ensemble Learning-Based Machine Learning Model for Phishing Attack

In today's world, the internet is increasingly effective in every aspect of our lives. The internet, which provides countless advantages when used consciously, also carries many dangers in its other aspect. One of these dangers and the most important one is the possibility of being targeted by malicious people while using the internet. Attackers can deceive innocent people by directing them to fake, misleading websites to obtain our important information and data. With this type of attack, known as phishing attack, internet users can provide their information and data to attackers. In this study, we propose a new ensemble learning-based machine learning model with feature selection methods to detect phishing attacks. We also try two feature selection algorithms to increase the classification success of the model and analyze the effects of these algorithms on the classification success. After the feature selection algorithms, the dataset with the selected features was trained with a new ensemble learning model that we created with the voting classifier method using XGBoost, CatBoost, LightGBM algorithms. The proposed model was analyzed using widely used performance evaluation metrics, achieving an accuracy of 97.96%. It was observed that the proposed model outperforms the studies in the literature using the same dataset.