International Journal of Electrical and Computer Engineering (IJECE) Vol. 13, No. 2, April 2023, pp. 2278~2288 ISSN: 2088-8708, DOI: 10.11591/ijece.v13i2.pp2278-2288  2278 Journal homepage: http://ijece.iaescore.com Intrusion detection method for internet of things based on the spiking neural network and decision tree method Ahmed R. Zarzoor 1 , Nadia Adnan Shiltagh Al-Jamali 2 , Dina A. Abdul Qader 2 1 Directorate of Inspection, Ministry of Health, Baghdad, Iraq 2 Department of Computer Engineering, University of Baghdad, Baghdad, Iraq Article Info ABSTRACT Article history: Received Apr 25, 2022 Revised Oct 16, 2022 Accepted Nov 8, 2022 The prevalence of using the applications for the internet of things (IoT) in many human life fields such as economy, social life, and healthcare made IoT devices targets for many cyber-attacks. Besides, the resource limitation of IoT devices such as tiny battery power, small storage capacity, and low calculation speed made its security a big challenge for the researchers. Therefore, in this study, a new technique is proposed called intrusion detection system based on spike neural network and decision tree (IDS-SNNDT). In this method, the DT is used to select the optimal samples that will be hired as input to the SNN, while SNN utilized the non-leaky integrate neurons fire (NLIF) model in order to reduce latency and minimize devices’ power usage. Also, a rand order code (ROC) technique is used with SNN to detect cyber-attacks. The proposed method is evaluated by comparing its performance with two other methods: IDS-DNN and IDS-SNNTLF by using three performance metrics: detection accuracy, latency, and energy usage. The simulation results have shown that IDS-SNNDT attained low power usage and less latency in comparison with IDS-DNN and IDS-SNNTLF methods. Also, IDS-SNNDT has achieved high detection accuracy for cyber-attacks in contrast with IDS-SNNTLF. Keywords: Deep neural network Internet of things Intrusion detection system Spike neural network This is an open access article under the CC BY-SA license. Corresponding Author: Ahmed R. Zarzoor Directorate of Inspection, Ministry of Health Baghdad, Iraq Email: Ahmed.Arjabi@gmail.com 1. INTRODUCTION Internet of things (IoT) smart devices are interconnected with each other, and to the internet via using protocols. Also, these devices are expanding rapidly and playing a pivotal role in human daily life. They have been used in many applications such as smart city, home, and car applications [1]–[3]. Consequently, there will be a community of interconnected smart things sharing and exchanging data in the world. Cisco company has foreseen that above than 200 billion smart things will be communicated to the internet via 2030 [4]. So, IoT devices are vulnerable to attacks besides their resource limitation making their data security the main challenge for researchers [5]. Moreover, it makes the security methods for key management, cyber-attacks detection, and trust management among the significant defies of the IoT network [6]. For instance, some researchers are handling security problems and defying the IoT network by using intrusion detection systems (IDS) [7]. The traditional IDS works on two levels: host level and network level [8]. The IDS works on the network level and is considered the most suitable secure method for the IoT network [9] due to the limitation of the IoT nodes’ resources (such as the low battery power and small storage capacity). Besides, the IoT network needs to be trained in either online traffic (i.e., live traffic) or offline (i.e., suitable dataset) in order to predict cyber-attacks. However, most researchers preferred to use the offline one to train the network because of the high cost of the online one [10].