Federated Radio Frequency Fingerprinting with Model Transfer and Adaptation
Federated Radio Frequency Fingerprinting with Model Transfer and Adaptation
复制标题
DOI：
10.1109/infocomwkshps57453.2023.10226112
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Chuanting Zhang;Shuping Dang;Junqing Zhang;Haixia Zhang;M. Beach
中科院分区：
文献类型：
--
作者：
Chuanting Zhang;Shuping Dang;Junqing Zhang;Haixia Zhang;M. Beach
射频（RF）指纹技术通过利用制造过程中引入的硬件缺陷，使未来网络的高度安全设备认证成为可能。虽然这种技术在过去几年中受到了相当大的关注，但RF指纹识别仍然面临着训练阶段和测试阶段之间的信道变化引起的数据分布漂移的巨大挑战。为了解决这一基本挑战并支持边缘的模型训练和测试，我们提出了一种联邦RF指纹识别算法，该算法采用了一种称为模型转移和自适应（MTA）的新策略。该算法将卷积层之间的密集连接引入到RF指纹中，以提高学习精度并降低模型复杂度。此外，我们在联邦学习的背景下实现了所提出的算法，使我们的算法通信效率和隐私保护。为了进一步克服数据不匹配的挑战，我们将学习模型从一个信道条件转移到其他信道条件，并使其适应其他信道条件，只有有限的信息量，从而在环境漂移下实现高度准确的预测。在真实数据集上的实验结果表明，该算法是模型不可知的，并且与信号无关。与现有的射频指纹识别算法相比，该算法可以显著提高预测性能，性能增益可达15%。
The Radio frequency (RF) fingerprinting technique makes highly secure device authentication possible for future networks by exploiting hardware imperfections introduced during manufacturing. Although this technique has received considerable attention over the past few years, RF fingerprinting still faces great challenges of channel-variation-induced data distribution drifts between the training phase and the test phase. To address this fundamental challenge and support model training and testing at the edge, we propose a federated RF fingerprinting algorithm with a novel strategy called model transfer and adaptation (MTA). The proposed algorithm introduces dense connectivity among convolutional layers into RF fingerprinting to enhance learning accuracy and reduce model complexity. Besides, we implement the proposed algorithm in the context of federated learning, making our algorithm communication efficient and privacy-preserved. To further conquer the data mismatch challenge, we transfer the learned model from one channel condition and adapt it to other channel conditions with only a limited amount of information, leading to highly accurate predictions under environmental drifts. Experimental results on real-world datasets demonstrate that the proposed algorithm is model-agnostic and also signal-irrelevant. Compared with state-of-the-art RF fingerprinting algorithms, our algorithm can improve prediction performance considerably with a performance gain of un to 15%.