Least Square Support Vector Machine based Intrusion Detection System in IoT

The IoT (Internet of Things) is an ever-expanding system of interconnected computing devices. It’s a term for when real-world items can communicate with one another via data transfers. The availability and dependability of its activities are crucial to the day-to-day functioning of modern society. As a result, it’s important to find a solution to the problem of ensuring secured data transmission across Internet of Things. An Intrusion Detection System (IDS) is a piece of software designed to keep an eye on a network or computer system and to address any suspicious activity. New threats and countermeasures must be incorporated into the network’s protected evolution. The primary function of IDS is to protect valuable resources against intrusion. Intruders can be spotted using various intrusion detection techniques, strategies, and algorithms. This major purpose of this study is to propose a comprehensive system for identifying intrusion risks by applying Least Squares Support Vector Machine approach. After receiving input, the following step is preprocessing, which was accomplished via Normalization, Discretization, and Feature selection in this study. These techniques are used for data preprocessing and feature selection. Training the model using LSSVM is the final stage. As compared to other models like SVM and RF, the proposed model attains an accuracy of roughly 97.7%.

I. Introduction

Many computers, cars, digital gadgets, sensors, etc. are now online and can communicate with one another as a consequence of the broad adoption of IoT concepts. Studies have concluded that the Internet’s large size and unregulated/anonymous structure make it challenging to keep corporate data and communications secure. Although most systems rely on firewalls to accomplish this, Intrusion Detection Systems (IDSs)is recognized as the system’s second line of defense, nonetheless play a significant part in ensuring system’s safety. Intruders are constantly seeking for new ways to get over the systems’ defences. Hence, IDSs must be integrated into all security architecture. Due to its unique applications and support for multiple sectors, including industrial process, healthcare, automation, smart environment, etc., the term “Internet of Things” (IoT) has become more common recently. Although IoT have far-reaching benefits, it also faces significant security risks. As Internet of Things (IoT) is a diverse ecosystem, and its interoperability mechanism does not lend itself to the use of tried-and-true security practices, new approaches are required. However, other aspects of security, such as data authentication, confidentiality, and access controls are improved in IoT. Despite the fact that these measures are intended to protect users’ data, Internet of Things still contains security issues. To ensure the security of the IoT network, it is essential to provide a dedicated module. Thus, concepts like Intrusion Detection System (IDS) are already ubiquitous in wireless networks. Improving intrusion detection system (IDS) capabilities in wireless networks can aid IoT in protecting networks from threats. The Internet of Things (IoT) is a network that enables things such as computers, robots, digital tools, physical objects, animals, and even humans to exchange data with one another in a decentralized fashion, without the need for human or machine intervention. In layman’s words, IoT bridges the gap between the real and the online. The aim behind the Internet of Things (IoT) is to create a network where physical devices and software can talk to one another in a way that both is secure and autonomous. Now, more than 11 billion IoT devices are linked and are in operation, as reported by IoT Analytics. Even more impressive is the fact that the number of IoT devices has increased by more than 10% since last year. A projected 21 billion IoT devices will be online by 2025 [1]. Hence, the IoT has grown rapidly in recent years as it has been adopted by several businesses and fields. These sectors include smart cities, smart homes, agriculture, transportation, logistics, healthcare and so on. Artificial intelligence (AI), big data, and fifth-generation (5G) wireless networks are all on the rise, and their integration with Internet of Things (IoT) is attracting with lot of interest. As Internet connects more and more people and things, the need for effectively protecting IoT components at every level, from physical to user, grows day by day. Hence, protecting the integrity of the network is crucial. Communications and computational components of Internet of Things are vulnerable to sophisticated hacking methods.