Semisupervised RF Fingerprinting With Consistency-Based Regularization
Weidong Wang, Cheng Luo, Jiancheng An, Lu Gan, Hongshu Liao, Chau Yuen
Abstract
As a promising non-password authentication technology, radio frequency (RF) fingerprinting can greatly improve wireless security. Recent work has shown that RF fingerprinting based on deep learning significantly outperforms conventional approaches. However, this superiority relies largely on using plenty of labeled data for supervised learning, whereas training deep neural networks on a small dataset generally falls into overfitting, resulting in performance degradation. Considering that it is often easier to obtain enough unlabeled data in practice, we leverage deep semisupervised learning for RF fingerprinting, which largely relies on a composite data augmentation scheme specifically designed for wireless communication signals, combined with two popular techniques: 1) consistency-based regularization and 2) pseudo-labeling. Experimental results on both simulated and real-world datasets demonstrate that our proposed method for semisupervised RF fingerprinting is far superior to other competing ones, and it achieves remarkable performance almost close to that of fully supervised learning, with a very limited number of examples available.