A Machine Learning Architecture Towards Detecting Denial of Service Attack in IoT

Internet of thing is part of our everyday life nowadays. Where millions of devices contented to the internet to collect and share data. Although IoT devices are evolving quickly to the consumer market where smart devices and sensors are becoming one of the main components of many households, IoT sensors and actuators have been also heavily used in the industry where thousands of devices are used to collect and share data for different purposes. With the rapid development of the Internet of Things in different areas, IoT is facing difficulty in securing overall availability of the network due to its heterogeneous nature. There are many types of vulnerability in IoT that can be mitigated with further research, however, in this paper, we have concentrated on distributed denial of Service attack (DDoS) on IoT. In this paper, we propose a machine learning architecture to detect DDoS attacks in IoT networks. The architecture collects IoT network traffic and analyzes the traffic through passing to machine learning model for attack detection. We propose the use of real-time data collection tool to dynamically monitor the network.