Comparative Study of Detection of IoT Attacks using Machine Learning Techniques

The term “Internet of Things” describes many trillions connected devices that share a single global data storage system. The Internet of Things has substantially altered our way of life due to the rise of techniques. However, IoT's quick spread to almost every aspect of life has given rise to several new cybersecurity threats. Therefore, academics and industry have recently shown a keen interest in identifying potential attacks in IoT networks because the Internet of things is facing the problem of security threats. A significant technological advancement in machine learning has created several fresh scientific possibilities to handle current and upcoming IoT issues. Machine learning, however, is a potent tool for finding risks and rumoured activity in networks and intelligent devices. This paper describes different types of attacks incurred in IoT devices and compares different machine-learning algorithms for detecting these attacks. The outcomes of various machine learning methods employed by various researchers to detect IoT attacks have been analysed in this study.