Multi-periodicity dependency Transformer based on spectrum offset for radio frequency fingerprint identification

TL;DR

This paper introduces MPDFormer, a novel Transformer-based model that enhances radio frequency fingerprint identification by leveraging spectrum offset-based periodic embeddings and a specialized attention mechanism to improve feature distinction amidst noise.

Contribution

The paper proposes a new Multi-Periodicity Dependency Transformer with spectrum offset embeddings and a periodicity-dependency attention mechanism for improved RFFI.

Findings

Achieves superior accuracy over baseline methods

Attains 0.07s inference time on NVIDIA Jetson Orin NX

Effectively mitigates background noise and weak periodicity effects

Abstract

Radio Frequency Fingerprint Identification (RFFI) has emerged as a pivotal task for reliable device authentication. Despite advancements in RFFI methods, background noise and intentional modulation features result in weak energy and subtle differences in the RFF features. These challenges diminish the capability of RFFI methods in feature representation, complicating the effective identification of device identities. This paper proposes a novel Multi-Periodicity Dependency Transformer (MPDFormer) to address these challenges. The MPDFormer employs a spectrum offset-based periodic embedding representation to augment the discrepency of intrinsic features. We delve into the intricacies of the periodicity-dependency attention mechanism, integrating both inter-period and intra-period attention mechanisms. This mechanism facilitates the extraction of both long and short-range periodicity-dependency features , accentuating the feature distinction whilst concurrently attenuating the perturbations caused by background noise and weak-periodicity features. Empirical results demonstrate MPDFormer's superiority over established baseline methods, achieving a 0.07s inference time on NVIDIA Jetson Orin NX.