An Adversarial-Driven Experimental Study on Deep Learning for RF Fingerprinting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Xinyu, Adhikari, Bimal, Zhao, Shangqing, Wu, Jingxian, Pan, Yanjun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914607769059328
author Cao, Xinyu
Adhikari, Bimal
Zhao, Shangqing
Wu, Jingxian
Pan, Yanjun
author_facet Cao, Xinyu
Adhikari, Bimal
Zhao, Shangqing
Wu, Jingxian
Pan, Yanjun
contents Radio frequency (RF) fingerprinting, which extracts unique hardware imperfections of radio devices, has emerged as a promising physical-layer device identification mechanism in zero trust architectures and beyond 5G networks. In particular, deep learning (DL) methods have demonstrated state-of-the-art performance in this domain. However, existing approaches have primarily focused on enhancing system robustness against temporal and spatial variations in wireless environments, while the security vulnerabilities of these DL-based approaches have often been overlooked. In this work, we systematically investigate the security risks of DL-based RF fingerprinting systems through an adversarial-driven experimental analysis. We observe a consistent misclassification behavior for DL models under domain shifts, where a device is frequently misclassified as another specific one. Our analysis based on extensive real-world experiments demonstrates that this behavior can be exploited as an effective backdoor to enable external attackers to intrude into the system. Furthermore, we show that training DL models on raw received signals causes the models to entangle RF fingerprints with environmental and signal-pattern features, creating additional attack vectors that cannot be mitigated solely through post-processing security methods such as confidence thresholds.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14109
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Adversarial-Driven Experimental Study on Deep Learning for RF Fingerprinting
Cao, Xinyu
Adhikari, Bimal
Zhao, Shangqing
Wu, Jingxian
Pan, Yanjun
Cryptography and Security
Machine Learning
Signal Processing
Radio frequency (RF) fingerprinting, which extracts unique hardware imperfections of radio devices, has emerged as a promising physical-layer device identification mechanism in zero trust architectures and beyond 5G networks. In particular, deep learning (DL) methods have demonstrated state-of-the-art performance in this domain. However, existing approaches have primarily focused on enhancing system robustness against temporal and spatial variations in wireless environments, while the security vulnerabilities of these DL-based approaches have often been overlooked. In this work, we systematically investigate the security risks of DL-based RF fingerprinting systems through an adversarial-driven experimental analysis. We observe a consistent misclassification behavior for DL models under domain shifts, where a device is frequently misclassified as another specific one. Our analysis based on extensive real-world experiments demonstrates that this behavior can be exploited as an effective backdoor to enable external attackers to intrude into the system. Furthermore, we show that training DL models on raw received signals causes the models to entangle RF fingerprints with environmental and signal-pattern features, creating additional attack vectors that cannot be mitigated solely through post-processing security methods such as confidence thresholds.
title An Adversarial-Driven Experimental Study on Deep Learning for RF Fingerprinting
topic Cryptography and Security
Machine Learning
Signal Processing
url https://arxiv.org/abs/2507.14109