High-Performance Phishing Email Detection Using Hybrid Machine Learning and Deep Learning Approaches

Phishing emails continue to represent a major cybersecurity threat, leveraging increasingly sophisticated social engineering techniques to evade conventional detection systems. Addressing this challenge requires intelligent and adaptive approaches capable of capturing both statistical patterns and contextual dependencies within email data. In this study, we propose a unified and robust phishing email detection framework that systematically integrates classical machine learning and advanced deep learning models within a consistent experimental pipeline. The novelty of this work lies in bridging feature-based learning and sequence-aware modeling through a standardized preprocessing and evaluation strategy, enabling a fair, reproducible, and comprehensive comparison across heterogeneous approaches. A wide range of machine learning algorithms, including Naive Bayes, Logistic Regression, SGDClassifier, XGBoost, Decision Tree, Random Forest, and MLPClassifier, are evaluated alongside deep learning architectures such as Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU). Experiments conducted on a large-scale email dataset demonstrate that traditional models achieve competitive performance, with accuracies ranging from 96.01% to 98.77%. However, deep learning models consistently outperform these approaches, reaching up to 99.9% accuracy by effectively capturing sequential and contextual information. The proposed framework highlights the effectiveness of combining structured feature engineering with deep sequential learning, offering a scalable and high-performance solution for real-world phishing detection. This work contributes to the advancement of intelligent cybersecurity systems capable of adapting to evolving and previously unseen phishing attacks.