Tracking UWB Devices Through Radio Frequency Fingerprinting Is Possible

2025-01-08

AI Summary

This work exposes a critical privacy vulnerability in commercial ultra-wideband (UWB) devices: their inherent radio-frequency fingerprints (RFFs) enable cross-environment tracking. Addressing the poor generalizability and environmental robustness of RFF extraction in UWB systems, we propose an end-to-end deep learning framework integrating time-frequency domain signal preprocessing, an enhanced CNN-LSTM hybrid architecture, and hardware fingerprint embedding learning. To our knowledge, this is the first systematic empirical validation of RFF-based tracking on real-world commercial UWB devices. Experimental results demonstrate >99% identification accuracy under stable conditions and—crucially—76% accuracy at previously unseen locations without retraining, substantially outperforming existing approaches. Our findings not only confirm a tangible privacy threat in off-the-shelf UWB hardware but also establish a new paradigm for RFF extraction that achieves both high environmental robustness and strong cross-scenario generalization.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Ultra-wideband (UWB) is a state-of-the-art technology designed for applications requiring centimeter-level localization. Its widespread adoption by smartphone manufacturer naturally raises security and privacy concerns. Successfully implementing Radio Frequency Fingerprinting (RFF) to UWB could enable physical layer security, but might also allow undesired tracking of the devices. The scope of this paper is to explore the feasibility of applying RFF to UWB and investigates how well this technique generalizes across different environments. We collected a realistic dataset using off-the-shelf UWB devices with controlled variation in device positioning. Moreover, we developed an improved deep learning pipeline to extract the hardware signature from the signal data. In stable conditions, the extracted RFF achieves over 99% accuracy. While the accuracy decreases in more changing environments, we still obtain up to 76% accuracy in untrained locations.

Problem

• Radio Frequency Fingerprinting
• Ultra-Wideband Devices
• Localization Accuracy and Privacy Protection

Innovation

• RFF Technology
• UWB Devices
• Machine Learning for Signal Processing