A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security

Abstract

The Internet of Things (IoT) integrates billions of smart devices that can communicate with one another with minimal human intervention. It is one of the fastest developing fields in the history of computing, with an estimated 50 billion devices by the end of 2020. On the one hand, IoT technologies play a crucial role in enhancing several real-life smart applications that can improve life quality. On the other hand, the crosscutting nature of IoT systems and the multidisciplinary components involved in the deployment of such systems have introduced new security challenges. Implementing security measures, such as encryption, authentication, access control, network security and application security, for IoT devices and their inherent vulnerabilities is ineffective. Therefore, existing security methods should be enhanced to secure the IoT ecosystem effectively. Machine learning and deep learning (ML/DL) have advanced considerably over the last few years, and machine intelligence has transitioned from laboratory curiosity to practical machinery in several important applications. The ability to monitor IoT devices intelligently provides a significant solution to new or zero-day attacks. ML/DL are powerful methods of data exploration for learning about 'normal' and 'abnormal' behaviour according to how IoT components and devices perform within the IoT environment. Consequently, ML/DL methods are important in transforming the security of IoT systems from merely facilitating secure communication between devices to security-based intelligence systems. The goal of this work is to provide a comprehensive survey of ML methods and recent advances in DL methods that can be used to develop enhanced security methods for IoT systems.IoT security threats that are related to inherent or newly introduced threats are presented, and various potential IoT system attack surfaces and the possible threats related to each surface are discussed. We then thoroughly review ML/DL methods for IoT security and present the opportunities, advantages and shortcomings of each method. We discuss the opportunities and challenges involved in applying ML/DL to IoT security. These opportunities and challenges can serve as potential future research directions.

Design Challenges of Multi-UAV Systems in Cyber-Physical Applications: A Comprehensive Survey and Future Directions

“…Using multi-UAVs in CPS applications can extend the attack surface of the systems that can include physical and cyber vulnerabilities. Moreover the introduction of internet of things (IoT) will enhance the applications of UAV systems [216]; on the other hand, the integration into IoT systems can enlarge the vulnerability surfaces of UAVs systems, because the IoT systems have several attack surfaces [217].Therefore, with the wide range of UAV applications, security is expected to be a high priority while designing UAVs. However, [218] showed that UAVs are not as secure as expected; this study reported that man-in-themiddle attack can be launched and the UAV can be controlled even with long distances from the main controller.…”

Machine Learning based Access Control Framework for the Internet of Things

“…In IoT, k-means clustering was used to distinguish Sybil attackers from normal sensors through clustering the channel vectors in industrial WSNs [20]. Nevertheless, this technique has many limitations, namely the need to have roughly equal numbers in each cluster for the algorithm to properly work, as well as the non-trivial task of choosing k [21]. Now, let us move to the deep sphere, and begin our survey by Convolutional Neural Networks (CNNs).…”

“…GANs may have a potential application in IoT security especially in zero-daylike threats given their ability to learn diverse attack scenarios and then to generate innovative attacks beyond the existing ones. Though, up to now the training phase of GANs still unstable and a tough task [21].…”

A Survey of Deep Learning Methods for Cyber Security

“…In [9], the authors reviewed and summarized work focusing on defending cyber-physical systems. Additionally, [10] reviews machine learning and DL methods for securing Internet of Things (IoT) technology. This paper is unique because it covers a wide array of cyber-attack types, and the approaches to detect them span a spectrum of DL techniques including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs).…”