[论文] Calibrated RF-Fingerprinting Under Interference With Heterogeneous Tra...

论文概要

研究领域: ML 作者: Tariq Abdul-Quddoos, Xiangfang Li, Lijun Qian 发布时间: 2026-09-17 arXiv: 2609.20765

中文摘要

射频（RF）指纹识别是一种频谱监测技术，它通过发射信号中烙有的硬件缺陷来识别特定发射机。尽管该方向已被广泛研究，但已有工作几乎只考虑同一时刻仅有一台发射机工作的场景，限制了其在真实环境中的应用。本文将研究推进到同信道干扰情形：多路信号在时域和频域上相互重叠、彼此干扰。具体而言，我们把该问题建模为多标签分类问题，并采用一维卷积神经网络（CNN）。此外，我们对模型进行校准，导出标签概率的置信度阈值，并对平均假阴性数的上界给出保证，从而确保在真实频谱违规发生时“不漏检”的可信度。所提方法在 POWDER 5G 测试床上采集的真实数据上验证，涉及 Wi-Fi（802.11a）、4G LTE 和 5G NR 波形。结果显示，校准后准确率视信道条件介于 73% 到 97% 之间；针对不同平均假阴性上界的校准可将 micro 召回率逼近 (1 - 校准假阴性率)，且校准对分布外干扰具有鲁棒性，展示了该方法在高竞争无线环境中的潜力。

原文摘要

Radio Frequency(RF)-Fingerprinting is a spectrum monitoring technique that identifies specific transmitters based on hardware impairments imprinted within the emitted signal. Although widely researched, studies almost exclusively consider scenarios where only one transmitter is emitting at a time, limiting real world applicability. In this work, we further the study of RF-Fingerprinting by considering co-channel interference, with multiple emitted signals interfering with each other, overlapping in time and frequency. Specifically, we formulate this problem as a multi-label classification problem and employ a 1D convolutional neural network (CNN). Furthermore, the models are calibrated such that the confidence thresholds for the label probabilities are derived, with guarantees on the upper...

#论文 #arXiv #ML #小凯