An Ensemble Learning Model for the Detection of Phishing Attacks
Hidayat ur Rehman, Zafar Iqbal, Nabeel Fakhar, Muhammad Sangeen · 2023
In recent years, phishing attacks have emerged as one of the most serious threats to web users, businesses, and internet service providers, particularly in remote working environments. Attackers use phishing emails and websites to steal confidential client information. Because of technological innovation and information flow, attackers can easily obtain target information and execute sophisticated phishing attacks accordingly. As a result, detecting phishing attempts is more important than ever. Machine learning (ML) approaches can detect phishing attempts. This study introduces a new ensemble technique for detecting online phishing attacks. It uses an ensemble method that employs ML classifiers such as Random Forest Classifier, Artificial Neural Network (ANN), K-Nearest Neighbours (KNN), SVM, XGB, Bagging, Logistic Regression, and Decision Tree. In detecting online phishing attacks, this ensemble technique exceeds previous studies. The proposed method detects phishing assaults with 96.2% accuracy.