Phishing emails remain a prominent cybersecurity threat, exploiting social engineering to compromise sensitive information. This study proposes a hybrid deep learning framework combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for real-time phishing email detection. The model automatically extracts discriminative textual and structural features while capturing sequential dependencies within email content. Experimental evaluations on two scenarios—controlled and complex datasets— demonstrated the superior performance of the proposed model compared to traditional classifiers, achieving up to 98.5% accuracy with high precision, recall, and F1-score. Results indicate robust performance across diverse email structures, highlighting practical applicability for operational deployment. The study contributes to the advancement of automated email security systems in dynamic environments.
Mohamed et al. (Mon,) studied this question.