Radio-frequency fingerprints (RFFs) are promising solutions for realizing low-cost physical layer authentication. Machine learning-based methods have been proposed for RFF extraction and discrimination. However, most existing methods are designed for the closed-set scenario where the set of devices is remains unchanged. These methods cannot be generalized to the RFF discrimination of unknown devices. To enable the discrimination of RFF from both known and unknown devices, we propose a new end-to-end deep learning framework for extracting RFFs from raw received signals. The proposed framework comprises a novel preprocessing module, called neural synchronization (NS), which incorporates the data-driven learning with signal processing priors as an inductive bias from communication-model based processing. Compared to traditional carrier synchronization techniques, which are static, this module estimates offsets by two learnable deep neural networks jointly trained by the RFF extractor. Additionally, a hypersphere representation is proposed to further improve the discrimination of RFF. Theoretical analysis shows that such a data-and-model framework can better optimize the mutual information between device identity and the RFF, which naturally leads to better performance. Experimental results verify that the proposed RFF significantly outperforms purely data-driven DNN-design and existing handcrafted RFF methods in terms of both discrimination and network generalizability.

中文翻译：

---

开放集 RFF 认证的通用模型和数据驱动方法


射频指纹（RFF）是实现低成本物理层身份验证的有前景的解决方案。基于机器学习的方法已经被提出用于 RFF 提取和区分。然而，大多数现有方法都是针对设备集保持不变的封闭集场景而设计的。这些方法不能推广到未知设备的 RFF 判别。为了能够区分已知和未知设备的 RFF，我们提出了一种新的端到端深度学习框架，用于从原始接收信号中提取 RFF。所提出的框架包括一个称为神经同步（NS）的新颖预处理模块，它将数据驱动学习与信号处理先验结合起来，作为基于通信模型的处理的归纳偏差。与静态的传统载波同步技术相比，该模块通过由 RFF 提取器联合训练的两个可学习深度神经网络来估计偏移。此外，还提出了超球面表示以进一步提高 RFF 的辨别力。理论分析表明，这样的数据和模型框架可以更好地优化设备身份和RFF之间的互信息，这自然会带来更好的性能。实验结果验证了所提出的 RFF 在辨别力和网络泛化性方面显着优于纯数据驱动的 DNN 设计和现有的手工 RFF 方法。