Enhancing internet of things security: evaluating machine learning classifiers for attack prediction

Abstract

The internet of things (IoT) has contributed to improving the quality of service and operational efficiency in many areas, such as smart cities, but this technology has faced a major dilemma: the problem of cyber-attacks of various types. In this study, we relied on the use of machine learning (ML) and deep learning (DL) techniques to present a proposed model of an intrusion detection system (IDS) for detecting different types of IoT attacks that include ARP_poisoning, DOS_SYN_Hping, MQTT_Publish, NMAP_FIN_SCAN, NMAP_OS_DETECTION, and Thing_Speak. However, the proposed model is built using Orange3 data mining tools. The model consists of random forest (RF), artificial neural network (ANN), logistic regression (LR), and support vector machine (SVM) classifiers. On the other hand, the data set that is used was obtained from the Kaggle platform's real-time IoT infrastructure data set, called RT-IoT2022. The data set consists of a huge number of records, which are processed and then reduced to 7,481 records using linear discriminant analysis. In the next stage, the data set is fed to the Orange3 data mining tool, which is divided into 70% of the training dataset and 30% of the test dataset, in addition to using fold-cross validation to increase accuracy and avoid overfitting. Thus, the experimental results showed the superiority of RF with a classification accuracy of (99.9%), while the accuracy in ANN reached (99.8%), (97.8%) in LR, and finally, for SVM, the accuracy reached (92.9%).