Abstract

Distributed Denial of Service (DDoS) is a malicious attempt to disrupt access to information, systems, networks, etc., by overwhelming systems and networks with traffics. Many methods for mitigating DDoS attacks have been proposed. In this paper, we present a systematic literature review of the application of machine learning methods in detecting a distributed denial of service (DDoS) attack. We have reviewed many research papers based on the methods that provided the best performance and evidence in machine learning technique applications. Our aim is to analyse, summarise and evaluate various machine learning methods for detecting DDoS attacks. We have evaluated five types of machine learning algorithms: Multi-Linear Regression, Deep Neural Network (DNN), Long Short-Term Memory (LSTM) method, Recurrent Neural Network (RNN) with Autoencoder, and LSTM with Singular Value Decomposition (SVD). We outline several open research questions, research techniques, parameters, and metrics. Also reviewed and contrasted were summaries of analyses and gaps in deploying a predictable machine learning model. Thus, the paper is expected to benefit academicians and researchers in developing an efficient solution for the machine learning mentioned above in detecting DDoS attacks.