This paper investigates the effectiveness of deep learning models in detecting phishing emails, focusing on one-dimensional CNN-based models (1D-CNNPD) and their enhancements with recurrent layers (LSTM, Bi-LSTM, GRU, and Bi-GRU). The study uses two benchmark datasets, Phishing Corpus and Spam Assassin, to evaluate the performance of these models. The results indicate that augmenting the base 1D-CNNPD model with recurrent layers generally improves performance, with the 1D-CNNPD model augmented with Bi-GRU achieving the best results. The advanced 1D-CNNPD model with Leaky ReLU and Bi-GRU achieved 100% precision, 99.68% accuracy, an F1 score of 99.66%, and a recall of 99.32%. The study highlights the potential of augmented 1D-CNNPD models in advancing cybersecurity solutions to combat email phishing attacks. The findings also suggest that increasing model depth initially improves performance but can lead to overfitting and subsequent degradation. The research contributes to the literature by assessing the impact of model complexity on phishing detection performance and providing recommendations for future research.This paper investigates the effectiveness of deep learning models in detecting phishing emails, focusing on one-dimensional CNN-based models (1D-CNNPD) and their enhancements with recurrent layers (LSTM, Bi-LSTM, GRU, and Bi-GRU). The study uses two benchmark datasets, Phishing Corpus and Spam Assassin, to evaluate the performance of these models. The results indicate that augmenting the base 1D-CNNPD model with recurrent layers generally improves performance, with the 1D-CNNPD model augmented with Bi-GRU achieving the best results. The advanced 1D-CNNPD model with Leaky ReLU and Bi-GRU achieved 100% precision, 99.68% accuracy, an F1 score of 99.66%, and a recall of 99.32%. The study highlights the potential of augmented 1D-CNNPD models in advancing cybersecurity solutions to combat email phishing attacks. The findings also suggest that increasing model depth initially improves performance but can lead to overfitting and subsequent degradation. The research contributes to the literature by assessing the impact of model complexity on phishing detection performance and providing recommendations for future research.