提出可解释的射频指纹特征学习方法，提升安全场景可信度。
Interpretable Feature Learning for RF Fingerprinting via Polar MKANs
- 将极坐标输入分块处理，显式分离幅度与相位特征
- 合成数据上解耦度达57.2%，远超基线的12.9%
- 适合对模型可解释性要求高的无线安全应用
射频指纹通过硬件引入的I/Q失真认证无线设备，传统深度学习方法虽准确但不可解释，限制其在安全关键场景的应用。本文提出极坐标单调柯尔莫哥洛夫-阿诺德网络（Polar MKAN），一种在极坐标输入上的分块单调编码器，每个潜在维度仅依赖幅度或相位，天然实现信道解耦与单调响应。在合成增益与载波频率偏移（CFO）基准测试中，Polar MKAN 的解耦度（DCI）达到57.2%，远超未分块基线的12.9%。进一步在真实数据上评估检测精度权衡及对盲式CFO补偿的敏感性。
原文摘要 · Abstract (English)
Radio frequency (RF) fingerprinting authenticates wireless devices from hardware-induced I/Q impairments, typically with deep learning feature extractors that are accurate but opaque, limiting their use in security critical settings. We propose Polar Monotonic Kolmogorov-Arnold Networks (Polar MKAN), a block partitioned monotonic encoder on polar inputs in which each latent dimension depends exclusively on magnitude or phase, yielding channel separation and monotone responses by construction. On a synthetic gain and carrier frequency offset (CFO) benchmark, Polar MKAN reaches 57.2 percent DCI Disentanglement versus at most 12.9 percent for unpartitioned baselines. We further evaluate the detection accuracy trade off on real data and the sensitivity to blind CFO compensation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。