Software-Defined Networking (SDN) is an innovative networking paradigm that offers exceptional manageability, scalability, control, and flexibility. However, despite these advantages, SDN is not inherently secure and remains vulnerable to various threats, including Denial of Service (DDoS) attacks. Among these, slow DDoS attacks are particularly challenging to detect. Recently, deep learning algorithms have shown promise in accurately identifying traffic anomalies. In this context, we propose using 1D Convolutional Neural Network model to detect slow DDoS attacks in SDN environments. Our method’s effectiveness is demonstrated using custom datasets, achieving impressive results with all performance metrics exceeding 99%. Furthermore, our model significantly outperforms other deep learning approaches like Multilayer Perceptron (MLP) and traditional machine learning models such as one-class Support Vector Machines (SVM).