Bluetooth Fingerprint Identification Under Domain Shift Through Transient Phase Derivative

2025-10-10

AI Summary

BLE devices suffer from poor robustness in radio-frequency (RF) fingerprinting under multi-source domain shifts—including time-varying conditions, device location, environmental variations, receiver heterogeneity, and channel dynamics. This paper first reveals the impact of BLE’s frequency-hopping mechanism on RF fingerprint stability and proposes a domain-adaptive feature extraction method based on transient phase derivatives. The method requires no additional hardware, ensuring low cost and strong cross-domain generalization. By leveraging deep learning to model phase dynamics, the extracted features effectively suppress domain-shift interference. Experiments demonstrate that our approach improves classification accuracy by up to 58% in cross-environment scenarios and 80% in cross-receiver settings—substantially outperforming existing baselines. This work provides a deployable, robust solution for physical-layer device authentication.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Deep learning-based radio frequency fingerprinting (RFFP) has become an enabling physical-layer security technology, allowing device identification and authentication through received RF signals. This technology, however, faces significant challenges when it comes to adapting to domain variations, such as time, location, environment, receiver and channel. For Bluetooth Low Energy (BLE) devices, addressing these challenges is particularly crucial due to the BLE protocol's frequency-hopping nature. In this work, and for the first time, we investigated the frequency hopping effect on RFFP of BLE devices, and proposed a novel, low-cost, domain-adaptive feature extraction method. Our approach improves the classification accuracy by up to 58% across environments and up to 80% across receivers compared to existing benchmarks.

Problem

• Addressing domain shift challenges in Bluetooth fingerprint identification
• Improving device authentication accuracy across varying environments and receivers
• Developing adaptive feature extraction for frequency-hopping BLE protocols

Innovation

• Uses transient phase derivative for feature extraction
• Addresses domain shift in Bluetooth fingerprint identification
• Improves accuracy across environments and receivers