Phishing remains one of the most prevalent and impactful forms of cybercrime on the Internet, leveraging social engineering tactics to deceive victims into divulging sensitive information such as login credentials or financial data. Scammers frequently masquerade as trusted organizations, exploiting users’ trust through private emails and fraudulent links. The emergence of global crises like the COVID-19 pandemic has further amplified phishing campaigns, with attackers capitalizing on fear and uncertainty to craft more convincing schemes. Despite advancements in email filtering technologies and cybersecurity measures, phishing detection methods often fall short of the required accuracy. Researchers continue to develop sophisticated solutions, with deep learning and Natural Language Processing (NLP) showing significant promise. In this work, we propose a phishing email detection model that combines NLP preprocessing steps with a one-dimensional Convolutional Neural Network (1D CNN). Our model processes textual data to identify phishing attempts with exceptional precision. Experimental results demonstrate that the proposed model achieves an accuracy of 99.99%, outperforming many existing approaches in both efficiency and reliability. To validate the practical application of our model, we integrated it into a mailing system, proving its robustness in detecting phishing emails in real-world scenarios.