Machine learning and datamining methods for hybrid IoT intrusion detection

By 2025 Internet of things will reach over 75 billion devices which would exceed number of humans about 8.1 billion. These devices need to be secured from many threats by implementing secure and interoperable solutions in order to guarantee a proper functioning of the infrastructures and systems using the IoT. This is why we proposed a hybrid intrusion detection system installed on the cloud powering another online and real time intrusion detection system on the fog to monitor the communication and detect attacks before it spreads over the network as in the case of Mirai botnet. We will provide details of the different algorithms used to implement this distributed system so as to detect attacks against IoT devices.