EPS: Distinguishable IQ Data Representation for Domain-Adaptation Learning of Device Fingerprints

TL;DR

This paper introduces EPS, a novel IQ data representation that significantly improves domain adaptation in RF fingerprinting, enabling more robust device identification across various conditions with high accuracy.

Contribution

The paper proposes the EPS representation, which captures device impairments while reducing domain variability, enhancing deep learning-based RF fingerprinting performance.

Findings

Achieves over 99% accuracy in same-day/channel/location tests

Attains 93% accuracy in cross-day evaluations

Reaches 95% accuracy in cross-location tests

Abstract

Deep learning (DL)-based RF fingerprinting (RFFP) technology has emerged as a powerful physical-layer security mechanism, enabling device identification and authentication based on unique device-specific signatures that can be extracted from the received RF signals. However, DL-based RFFP methods face major challenges concerning their ability to adapt to domain (e.g., day/time, location, channel, etc.) changes and variability. This work proposes a novel IQ data representation and feature design, termed Double-Sided Envelope Power Spectrum or EPS, that is proven to overcome the domain adaptation problems significantly. By accurately capturing device hardware impairments while suppressing irrelevant domain information, EPS offers improved feature selection for DL models in RFFP. Experimental evaluations demonstrate its effectiveness, achieving over 99% testing accuracy in same-day/channel/location evaluations and 93% accuracy in cross-day evaluations, outperforming the traditional IQ representation. Additionally, EPS excels in cross-location evaluations, achieving a 95% accuracy. The proposed representation significantly enhances the robustness and generalizability of DL-based RFFP methods, thereby presenting a transformative solution to IQ data-based device fingerprinting.