This study investigates the effectiveness of deep learning models, specifically 1D-CNN-based models, for detecting phishing emails. The research compares the performance of various deep learning models, including 1D-CNNPD, LSTM, Bi-LSTM, GRU, and Bi-GRU, using two benchmark datasets: Phishing Corpus and Spam Assassin. The results show that augmenting the 1D-CNNPD model with Bi-GRU significantly improves performance, achieving 100% precision, 99.68% accuracy, an F1 score of 99.66%, and a recall of 99.32%. The study also highlights the trade-off between model depth and performance, noting that while deeper models initially improve performance, they may lead to overfitting and reduced effectiveness. The 1D-CNNPD with Bi-GRU outperforms other deep learning and machine learning models in phishing detection. The study concludes that deep learning models, particularly CNNs, are effective in detecting phishing emails with high accuracy and efficiency, offering a promising solution for improving cybersecurity measures against email phishing attacks. The results demonstrate the potential of these models in enhancing the detection of phishing emails and reducing false positives.This study investigates the effectiveness of deep learning models, specifically 1D-CNN-based models, for detecting phishing emails. The research compares the performance of various deep learning models, including 1D-CNNPD, LSTM, Bi-LSTM, GRU, and Bi-GRU, using two benchmark datasets: Phishing Corpus and Spam Assassin. The results show that augmenting the 1D-CNNPD model with Bi-GRU significantly improves performance, achieving 100% precision, 99.68% accuracy, an F1 score of 99.66%, and a recall of 99.32%. The study also highlights the trade-off between model depth and performance, noting that while deeper models initially improve performance, they may lead to overfitting and reduced effectiveness. The 1D-CNNPD with Bi-GRU outperforms other deep learning and machine learning models in phishing detection. The study concludes that deep learning models, particularly CNNs, are effective in detecting phishing emails with high accuracy and efficiency, offering a promising solution for improving cybersecurity measures against email phishing attacks. The results demonstrate the potential of these models in enhancing the detection of phishing emails and reducing false positives.