# Radio Frequency Fingerprint Identification Based on Denoising Autoencoders

## TL;DR

This paper introduces a Denoising Autoencoder-based model for radio frequency fingerprinting that significantly improves device identification accuracy in low SNR environments, enhancing IoT security.

## Contribution

The paper proposes a novel PSC-DAE model with a stacking method to effectively reconstruct high-SNR signals and identify devices under noisy conditions.

## Key findings

- PSC-DAE improves identification accuracy by 14-23.5% at low SNRs
- Achieves 97.5% accuracy at 10 dB SNR
- Outperforms traditional CNN in noisy environments

## Abstract

Radio Frequency Fingerprinting (RFF) is one of the promising passive authentication approaches for improving the security of the Internet of Things (IoT). However, with the proliferation of low-power IoT devices, it becomes imperative to improve the identification accuracy at low SNR scenarios. To address this problem, this paper proposes a general Denoising AutoEncoder (DAE)-based model for deep learning RFF techniques. Besides, a partially stacking method is designed to appropriately combine the semi-steady and steady-state RFFs of ZigBee devices. The proposed Partially Stacking-based Convolutional DAE (PSC-DAE) aims at reconstructing a high-SNR signal as well as device identification. Experimental results demonstrate that compared to Convolutional Neural Network (CNN), PSCDAE can improve the identification accuracy by 14% to 23.5% at low SNRs (from -10 dB to 5 dB) under Additive White Gaussian Noise (AWGN) corrupted channels. Even at SNR = 10 dB, the identification accuracy is as high as 97.5%.