Domain Generalization for Cross-Receiver Radio Frequency Fingerprint Identification

TL;DR

This paper introduces a novel approach for cross-receiver radio frequency fingerprint identification that leverages a theoretical error bound, a receiver-independent model, and federated learning to improve device identification accuracy across different receivers.

Contribution

It proposes a theoretical analysis of generalization error, a receiver-independent identification model, and a federated learning framework for cross-receiver RFFI.

Findings

The proposed methods outperform baseline approaches in real-world datasets.

Theoretical analysis provides a sufficient condition to reduce classification error.

Federated learning enables decentralized training without raw data sharing.

Abstract

Radio Frequency Fingerprint Identification (RFFI) technology uniquely identifies emitters by analyzing unique distortions in the transmitted signal caused by non-ideal hardware. Recently, RFFI based on deep learning methods has gained popularity and is seen as a promising way to address the device authentication problem for Internet of Things (IoT) systems. However, in cross-receiver scenarios, where the RFFI model is trained over RF signals from some receivers but deployed at a new receiver, the alteration of receivers' characteristics would lead to data distribution shift and cause significant performance degradation at the new receiver. To address this problem, we first perform a theoretical analysis of the cross-receiver generalization error bound and propose a sufficient condition, named Separable Condition (SC), to minimize the classification error probability on the new receiver. Guided by the SC, a Receiver-Independent Emitter Identification (RIEI)model is devised to decouple the received signals into emitter-related features and receiver-related features and only the emitter-related features are used for identification. Furthermore, by leveraging federated learning, we also develop a FedRIEI model to eliminate the need for centralized collection of raw data from multiple receivers. Experiments on two real-world datasets demonstrate the superiority of our proposed methods over some baseline methods.