A Comparative Performance Analysis of Machine Learning and Hybrid Deep Learning Models for Phishing Email Detection

This paper presents a comparative performance analysis of traditional machine learning classifiers and a hybrid CNN-LSTM deep learning model for phishing email detection. The study evaluates multiple models including K-Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, and the proposed CNN-LSTM architecture. Experiments are conducted under controlled and heterogeneous scenarios using standard evaluation metrics such as accuracy, precision, recall, and F1-score. Results demonstrate that the hybrid CNN-LSTM model consistently achieves superior performance and robustness compared to conventional machine learning approaches, making it suitable for real-time phishing email detection in cybersecurity applications.