Practical Fingerprinting of RF Devices in the Wild

TL;DR

This paper introduces a practical RF fingerprinting method using delay-loop reservoir computing and Ridge Regression, capable of identifying wireless devices even under challenging conditions like fading and jamming.

Contribution

The work presents a novel RF fingerprinting approach combining delay-loop reservoir computing with Ridge Regression, enhancing robustness for IoT device authentication in noisy environments.

Findings

MF-DLR improves device identification accuracy in fading channels.

MF processing enhances SEI performance of RR without RC transformation.

The method is effective for signatures beyond waveform transients, such as turn-on signals.

Abstract

We present a new RF fingerprinting technique for wireless emitters that is based on a simple, easily and efficiently retrainable Ridge Regression (RR) classifier. The RR learns to identify devices using bursts of waveform samples, conveniently transformed and preprocessed by delay-loop reservoirs. Deep delay Loop Reservoir Computing (DLR) is our processing architecture that supports general machine learning algorithms on resource-constrained devices by leveraging delay-loop reservoir computing (RC) and innovative architectures of loop trees. In prior work, we trained and evaluated DLR using high SNR device emissions in clean channels. We here demonstrate how to use DLR for IoT authentication by performing RF-based Specific Emitter Identification (SEI), even in the presence of fading channels and heavy in-band jamming by leveraging a matched filter (MF) extension, dubbed MF-DLR. We show that the MF processing improves the SEI performance of RR without the RC transformation (MF-RR), but the MF-DLR is more robust and applicable for addressing signatures beyond waveform transients (e.g. turn-on).