Mechine And Learning Based IoT Instruion Detection

Abstract

In today’s world, technological advancements are gradually increasing, so small scale to large scale companies use the internet for business purposes. Other than that Internet of Things (IoT) is a current trend in the world. Most companies try to improve their companies by making them smart premises since this will give a lot of advantages; some are increasing customer satisfaction, saving time, control expenses, monitoring, and many more. So, with the rise of these technological advancements, diverse types of security issues like DDoS, malware, virus, worms, and many other issues occurs as well because of the software or device vulnerabilities. These are harmful to organizations’ sensitive data due to the violation of integrity, confidentiality, and availability. IoT devices have been extensively implemented in many different applications in recent years, such as smart homes, medical, heavy industry, agriculture, networks, security, transportation, etc. An adversary can capture the network traffic of IoT devices and analyze it to reveal user activities even if the traffic is encrypted. Due to the increasing number of cyber-attacks, we need IoT security solutions. The majority of the attacks are extended versions of previously known attacks and bypass the conventional firewall system. An Intrusion Detection System (IDS) performed an incredibly significant part to figure out the novel types of attacks by analyzing the network traffic. Machine Learning (ML) and Deep Learning (DL) based techniques such as Random Forest (RF), Support Vector Machine (SVM), J48, Naïve Bayes (NB), Logistic Regression (LR), etc. are used as a classifier to categorize the network traffic as normal and attack class. The objective of this research is to compare the impact of different Feature Selection (FS) techniques such as Information Gain (IG), Chi-Square, Correlation-based Feature Selection (CFS) subsets evaluator, Classifier based attributes, and other techniques on the accuracy, computational time and confusion matrix of ML & DL based techniques and identify the attack categories. FS methods and classifiers have been implemented on four different data sets NSL KDD, UNSW-15, CIC IDS2017, and TON_IoT and a comparative assessment of the outcome is presented. By applying our proposed comparative model, we will be able to trace out the malicious attacks i.e., DoS, DDoS, routing attacks, Man-in-The-Middle (MITM), etc. in the realm of IoT networks. This model detects the attacks with high accuracy and consumes less time as compared to the other methods.