Where You Tap Matters: A Probe-and-Model Benchmark for Open-Set RF Fingerprinting

2026-07-23

AI Summary

This study addresses the unclear impact of receiver-chain sampling positions on open-set radio frequency fingerprint identification (RFFI) performance, a key factor hindering result reproducibility. The authors systematically evaluate five critical probe points within a standard BPSK receiver chain under a unified preprocessing pipeline and mean squared error (MSE)-based scoring mechanism, comparing multiple autoencoder architectures. Their empirical analysis reveals, for the first time, that probe location is the dominant factor influencing RFFI performance—surpassing model complexity—with timing and carrier recovery stages yielding the best trade-off: achieving true acceptance rates ≥0.9 at false acceptance rates <0.1. In contrast, other stages exhibit significantly degraded performance. To support future research, the work also introduces a standardized benchmarking framework to ensure reproducibility.

Abstract

Radio Frequency Fingerprint Identification (RFFI) enables transmitter identification at the physical layer by learning device-specific impairments from received signals, yet the literature is inconsistent about where in the receiver chain those samples should be collected. Since distinct transformations are applied to the signal by the different receiver operations, i.e., carrier recovery, gain normalization, pulse shaping, and timing recovery, they can either tighten within-transmitter variability or suppress the features RFFI requires for classification. We present a systematic real-world evaluation of open-set, reconstruction-error RFFI using data collected at five probe points along a standard BPSK receiver chain. Our results show that RFFI is strongly probe-dependent: timing recovery and, to a lesser extent, carrier recovery enable low false-acceptance operation with limited in-distribution-out-of-distribution overlap, whereas other stages often require a false-acceptance ratio above 0.1 to achieve a true-acceptance ratio of 0.9. To test the validity of our findings across model selection, we benchmark several LLM-designed autoencoders using a controlled pipeline that holds preprocessing and MSE scoring fixed. These architectures confirm that RFFI is probe-dependent. Moreover, they do not outperform the baseline at the chosen operating point and typically increase training time. Overall, probe selection dominates reconstruction-based open-set RFFI performance, more than the autoencoder complexity.

Problem

• RF Fingerprinting
• Open-Set Recognition
• Probe Point
• Receiver Chain
• Transmitter Identification

Innovation

• RF fingerprinting
• probe-dependent
• open-set identification
• reconstruction-based RFFI
• receiver chain analysis