IDS for IoT environment using machine learning techniques
Loading...
Date
2023
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
UMT, Lhr
Abstract
The Internet of Things (IoT) is a technology that is experiencing rapid growth. It involves connecting billions of smart objects and sensors to the Internet for the purpose of collecting data from the physical environment. However, the presence of security vulnerabilities in IoT-based systems creates a significant threat to smart environment applications. Due to the high volume, variety, and high speed of data generated in the network, traditional techniques for detecting attacks are often inadequate. This leads to a crucial need for robust security mechanisms or intrusion detection systems (IDSs) designed for IoT environments to mitigate security attacks that exploit these vulnerabilities. An IDS is a system that monitors and analyzes data to detect intrusions in the system or network. Our primary objective is to construct an IDS system that uses machine-learning models to detect various types of attacks and adapt to their changing nature. The Decision Tree Algorithm is the chosen method for this system, as it provides 99% accurate results with low false-positive and false-negative rates. We have evaluated the effectiveness of this system using a real-world IoT dataset. It is essential to establish a robust security mechanism or IDS for IoT environments to address security threats effectively. By utilizing machine-learning models such as the Decision Tree Algorithm, the proposed IDS system can detect various types of attacks and adapt to their changing nature. It is hoped that this system will provide a high level of security and be effective in mitigating security attacks that exploit the vulnerabilities of IoT-based systems