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

Abstract

<p>A novel cross-domain attentional multi-task architecture - xDom - for robust real-world wireless radio frequency (RF) fingerprinting is presented in this work.</p> <p>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.</p>

Fine-Grained Radio Frequency Fingerprint Recognition Network Based on Attention Mechanism

“…The network structure is relatively simple, which limits further improvement to its accuracy. Some works used general architectures in computer vision classification to classify RF fingerprints, such as 1D modified versions of AlexNet (AlexNet1D) and ResNet-50 (ResNet1D) [15,16], VGG-16 [17], attention mechanism [18], and so on. The researchers modified the convolution kernel to be one-dimensional to make it suitable for the 1D RF signals without considering a network architecture specifically applicable to the existing challenges of RF fingerprint recognition.…”

“…In the past few decades, many efforts have been made for RF-fingerprint-based recognition, and they can be classified into two categories: machine-learning-based [7][8][9][10][11][12][13] and deep-learning-based methods [14][15][16][17][18][19][20][21][22]. The former requires manually extracting the designed and specific RF fingerprint features from the RF signal and then using a classifier to identify the device.…”