Identification of OFDM-Based Radios Under Rayleigh Fading Using RF-DNA and Deep Learning

Mohamed K M Fadul,Mina Sartipi,Donald R Reising

doi:10.1109/access.2021.3053491

Mohamed K M Fadul, Mina Sartipi + Show 1 more

Open Access

https://doi.org/10.1109/access.2021.3053491

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2021
Citations: 63	License type: CC BY 4.0

Affiliation: University of Tennessee at Chattanooga

Abstract

The Internet of Things (IoT) is here and has permeated every aspect of our lives. A disturbing fact is that the majority of all IoT devices employ weak or no encryption at all. This coupled with recent advances within the areas of computational power and deep learning has increased interest in Specific Emitter Identification (SEI) as an effective means of IoT security. Deep learning is capable of in-situ extraction of discriminating features, making it well suited to discrimination of wireless transmitters without the need for feature engineering. However, the accuracy of the deep learning model is adversely affected by time-varying channel conditions. The time-varying nature is attributed to the mobility of the transmitter, receiver, objects within the operations environment, or combinations thereof. This can result in the channel conditions changing faster than the deep learning algorithm is capable of handling. This paper assesses deep learning-based SEI using waveforms that undergo Rayleigh fading, as well as channel estimation and equalization, prior to being input into a deep learning algorithm.

Highlights

The Internet of Things (IoT) is here and has permeated every aspect of our lives both personal and professional
SIGNAL COLLECTION, DETECTION, AND POST-PROCESSING radio frequency (RF)-DNA fingerprint–based Specific Emitter Identification (SEI) uses a portion of the transmitted waveform that corresponds with a fixed, known sequence of symbols used by the receiver to perform synchronization and channel equalization to facilitate demodulation
Each of the NB = 2, 000 preambles is convolved with a unique Rayleigh channel and like-filtered, scaled Additive White Gaussian Noise (AWGN)

Summary

Introduction

The Internet of Things (IoT) is here and has permeated every aspect of our lives both personal and professional. A disturbing fact of this rapid growth is that the majority, roughly 70%, of all IoT devices fail to use encryption due to (i) on-board computation restrictions, (ii) the manufacturer’s cost of implementation being too high, and (iii) implementation and management challenges that are exacerbated at scale [5]–[7]. This lack of security makes IoT devices and the corresponding infrastructure open to attacks by devices that are incorrectly authenticated—often due to their use of compromised digital credentials that have been transmitted in the clear. Post-processing consists of carrier frequency offset correction and re-sampling to a sampling rate of 20 MHz

Methods

Results

Conclusion