Application of Multiclassification for Detecting Intrusions in IoT and Their Type Recognizing

The goal of the work is to identify the possibility of using machine learning algorithms with a multiclass approach to detect attacks in Internet of Things (IoT) networks, determine their type, improve the security of IoT devices, protect devices and their users from attackers. The experimental results show that the proposed multi-layer gradient boosting classifier model can achieve better prediction of small classes without sacrificing the prediction performance of numerous classes, but requires much more time than other methods. The second algorithm that has good accuracy is the Extra Trees algorithm with affordable detection time. At the same time, the method has good learning efficiency indicators. This means that this algorithm can be deployed and applied with the greatest success.