Detection of DDoS Attacks in Networks Using CRNN

Abstract

The main objective of this paper is to detect DDoS attacks in network through Deep Learning techniques. Distributed Denial of Service (DDoS) imposes possible threats which exhaust the resources to make it unavailable for the legitimate user by violating one of the security components [1]. In the field of DDoS attacks, as in all other areas of cyber security, attackers are increasingly using sophisticated methods [2]. Various machine learning techniques could be used to address the security issues effectively and efficiently. In this paper, we present a new technique for combination of deep learning models that can be used for network traffic. We show that a Recurrent Neural Network (RNN) combined with a Convolutional Neural Network (CNN), CRNN (Convolutional Recurrent Neural Network) model provides best detection results. A complete study is presented on several architectures that integrate a CNN and an RNN, including the impact of the features chosen and the length of the network flows used for training.