Enhancing IoT security with radio frequency fingerprinting: traditional and deep learning-based approaches

The Internet of Things (IoT) has revolutionized real-time data collection, remote monitoring, and automation, connecting a vast number of devices within the IoT ecosystem. However, this rapid growth comes with its security concerns, such as unauthorized access and data breaches. In this chapter, we discuss the application of Radio Frequency Fingerprinting (RFF) techniques for enhancing the security of the IoT devices and networks. Various types of RFF techniques, ranging from traditional classical approaches to state-of-the-art deep learning-based approaches, are presented and discussed. For conventional RFF techniques, we explore transient- and steady-state signal-based techniques. We then discuss various deep learning-based RFF approaches, focusing on their feature engineering methods. The latest trends in RFF techniques are provided along with a summary of future research challenges. Further research is expected to be carried out to make RFF techniques a crucial part of the IoT networks and pave the way to address security challenges.