Key points are not available for this paper at this time.
The Internet of Things (IoT) integrates billions of smart devices that can with one another with minimal human intervention. It is one of the developing fields in the history of computing, with an estimated 50 devices by the end of 2020. On the one hand, IoT play a crucial role in several real-life smart applications that can improve life quality. the other hand, the crosscutting nature of IoT systems and the components involved in the deployment of such systems new security challenges. Implementing security measures, such as, authentication, access control, network security and application, for IoT devices and their inherent vulnerabilities is ineffective. , existing security methods should be enhanced to secure the IoT effectively. Machine learning and deep learning (ML/DL) have advanced over the last few years, and machine intelligence has transitioned laboratory curiosity to practical machinery in several important. Consequently, ML/DL methods are important in transforming the of IoT systems from merely facilitating secure communication between to security-based intelligence systems. The goal of this work is to a comprehensive survey of ML /DL methods that can be used to develop security methods for IoT systems. IoT security threats that are to inherent or newly introduced threats are presented, and various IoT system attack surfaces and the possible threats related to each are discussed. We then thoroughly review ML/DL methods for IoT security present the opportunities, advantages and shortcomings of each method. We the opportunities and challenges involved in applying ML/DL to IoT. These opportunities and challenges can serve as potential future directions.
Al-Garadi et al. (Sun,) studied this question.