Detecting DDoS Attacks Using an Adaptive-Wavelet Convolutional Neural Network
Maryam Ghanbari, Witold Kinsner · 2021
This paper introduces an architecture of a convolutional neural network (CNN) to detect a distributed denial of service (DDoS) attack. The main procedure is the application of an adaptive mother wavelet that is created using a genetic neural network (GNN) to increase the detection rate of the DDoS. In addition, an adaptive-wavelet CNN is trained to extract features from Internet traffic containing DDoS attacks to classify the Internet traffic data (ITD) with DDoS attacks (DDoS ITD) as normal or anomalous. Moreover, a multi-objective optimization based on a genetic algorithm and a weighted cost function based on an information-theoretic measure are used to train and evaluate the adaptive-wavelet CNN. Finally, the adaptive-wavelet CNN's classification efficiency is assessed to find the detection rate of the proposed architecture. The adaptive-wavelet CNN detects the DDoS attack with 95% accuracy.