SDN-DDoSNet: A Deep Learning Framework for DDoS Attack Detection in Software-Defined Networks

Distributed Denial of Service (DDoS) attack is a malicious attempt to disrupt normal web traffic, posing an increasing threat to network infrastructures due to the growing frequency and sophistication of such attacks. This necessitates the development of robust and adaptive defense mechanisms. In this research, we propose a deep learning-based approach for DDoS attack detection, leveraging a Software-Defined Net-working dataset. Our study explores three models: Long-short-term memory,convolutional neural network, and hybrid CNN-LSTM architecture, each designed to capture the temporal and spatial features inherent in network traffic data. The data set includes diverse attack scenarios, including UDP, ICMP, and SYN protocol. The LSTM model achieved an accuracy of 99. 61% in the SDN- DDOS data set, followed by the hybrid model at 99.24%, and the CNN model at 98.86%.