DDoS Attack Intrusion Detection System Based on Hybridization of CNN and LSTM
Ahmet Sardar Ahmed Issa, Zafer Albayrak
Abstract
A distributed denial-of-service (DDoS) attack is one of the most pernicious threats to network security. DDoS attacks are considered one of the most common attacks among all network attacks. These attacks cause servers to fail, causing users to be inconvenienced when requesting service from those servers. Because of that, there was a need for a powerful technique to detect DDoS attacks. Deep learning and machine learning are effective methods that researchers have used to detect DDoS attacks. So, in this study, a novel deep learning classification method was proposed by mixing two common deep learning algorithms, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM). The NSL-KDD dataset was used to test the model. This method architecture consists of seven layers to achieve higher performance compared with traditional CNN and LSTM. The proposed model achieved the highest accuracy of 99.20% compared with previous work. © 2023, Budapest Tech Polytechnical Institution. All rights reserved.