RF Fingerprinting Needs Attention: Multi-task Approach for Real-World WiFi and Bluetooth

TL;DR

This paper introduces xDom, a novel multi-task attention-based architecture for real-world RF fingerprinting of WiFi and Bluetooth devices, demonstrating significant performance improvements in complex indoor environments.

Contribution

The work presents the first comprehensive attention mechanism applied to RF fingerprinting using real-world IoT emissions in multipath and interference conditions.

Findings

Up to 59.3% performance improvement in WiFi fingerprinting.

Up to 4.91x accuracy gain over state-of-the-art models.

50.5% increase in multi-task fingerprinting accuracy.

Abstract

A novel cross-domain attentional multi-task architecture - xDom - for robust real-world wireless radio frequency (RF) fingerprinting is presented in this work. To the best of our knowledge, this is the first time such comprehensive attention mechanism is applied to solve RF fingerprinting problem. In this paper, we resort to real-world IoT WiFi and Bluetooth (BT) emissions (instead of synthetic waveform generation) in a rich multipath and unavoidable interference environment in an indoor experimental testbed. We show the impact of the time-frame of capture by including waveforms collected over a span of months and demonstrate the same time-frame and multiple time-frame fingerprinting evaluations. The effectiveness of resorting to a multi-task architecture is also experimentally proven by conducting single-task and multi-task model analyses. Finally, we demonstrate the significant gain in performance achieved with the proposed xDom architecture by benchmarking against a well-known state-of-the-art model for fingerprinting. Specifically, we report performance improvements by up to 59.3% and 4.91x under single-task WiFi and BT fingerprinting respectively, and up to 50.5% increase in fingerprinting accuracy under the multi-task setting.