IoT DDoS attacks detection using machine learning techniques: A Review

Abstract

Internet of things (IoT) is the paradigm that is revolutionizing our daily lives. It has become an important part of our lives due to its ability to transform lives. More and more organizations are using IoT devices as they open new opportunities for healthcare, wearable devices, home appliances and improve sharing and communication of information using the internet. With all these opportunities the challenges related to IoT security are rising. The limited resources and open deployment environment makes it vulnerable to several malicious attacks such as Distributed Denial of service (DDoS). Traditional detection approaches are inadequate for current security requirements. By applying the machine learning techniques these approaches can be improved which in turn will result in improved security. Therefore, this paper is a review of current advancements made in the application of machine learning techniques for the detection of DDoS attacks in IoT. There are many survey papers on intrusion detection in IoT but there is very little which particularly focuses on DDoS attacks. As more and more organizations are using IoT devices, but due to lack of knowledge they sometimes find it hard to understand how to ensure security, this paper will serve as a guide, as its main contribution is to provide an overview of the current state of the art of applications of machine learning techniques in the detection of Distributed Denial of Service attacks in IoT. This paper will also add to the knowledge of researchers who are interested in IoT security.