Towards an Efficient DDoS Attack Detection in SDN: An Approach with CNN-GRU Fusion

The emergence of Distributed Denial of Service (DDoS) attacks presents a significant risk to Software-Defined Networking (SDN) services. This study focuses on developing an effective method for detecting DDoS attacks in SDN by leveraging Deep Learning (DL) techniques, precisely combining Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). This research proposes a novel approach that utilizes CNN-GRU-based DL models to detect DDoS attacks in SDN accurately. This approach learns intricate patterns and temporal dependencies associated with DDoS attacks by analyzing network traffic data and detecting such threats. In order to assess the effectiveness of our model, we conduct extensive experiments using diverse datasets comprising both normal network traffic and various types of DDoS attacks. We present a comparative analysis against traditional ML algorithms and existing methodologies. To assess the effectiveness of our approach, we used various performance metrics. The experimental results prove that the CNN-GRU-based DL model outperforms other techniques, exhibiting superior accuracy and overall performance in detecting DDoS attacks in SDN.