Detection of cyber attacks in IoT using tree-based ensemble and feedforward neural network

Abstract

Detection of cyber attacks in the Internet of Things (IoT) networks has lately been a growing concern. Due to the extensive use of IoT infrastructures in numerous domains, these malicious attacks are also increasing continuously and changing over time. Moreover, devices connected in IoT networks are operated without any human intervention for longer times. Hence, intelligent network-based security solutions are very important to provide timely detection of these attacks to protect an IoT system from potential failure. Different machine learning based techniques have already been proposed to provide effective solution to discover and counteract network intrusion aiming to ensure security in the network. In the context of IoT networks, little attention has been paid to the identification of malicious attacks. To this end, we propose an effective intrusion detection system (IDS) to detect unforeseen IoT cyberattacks by using various bagging and boosting ensemble methods and feed forward artificial neural network. We have used a recently published dataset, UNSW-NB15, containing simulated IoT sensor data to estimate the performance of the proposed models through 5-fold cross validation technique. The performance results show the effectiveness of the models with a small set of automatically selected optimal features from the dataset.