Semi-Supervised RF Fingerprinting with Consistency-Based Regularization

TL;DR

This paper introduces a semi-supervised deep learning approach for RF fingerprinting that effectively utilizes unlabeled data through consistency regularization and data augmentation, achieving near-supervised performance with limited labeled samples.

Contribution

It proposes a novel semi-supervised RF fingerprinting method combining data augmentation, consistency regularization, and pseudo-labeling, addressing data scarcity issues in practical scenarios.

Findings

Outperforms existing semi-supervised methods on simulated and real datasets.

Achieves near-supervised accuracy with minimal labeled data.

Demonstrates robustness and practicality of the approach.

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 can significantly outperform conventional approaches. The superiority, however, is mainly attributed to supervised learning using a large amount of labeled data, and it significantly degrades if only limited labeled data is available, making many existing algorithms lack practicability. Considering that it is often easier to obtain enough unlabeled data in practice with minimal resources, we leverage deep semi-supervised learning for RF fingerprinting, which largely relies on a composite data augmentation scheme designed for radio signals, combined with two popular techniques: consistency-based regularization and pseudo-labeling. Experimental results on both simulated and real-world datasets demonstrate that our proposed method for semi-supervised RF fingerprinting is far superior to other competing ones, and it can achieve remarkable performance almost close to that of fully supervised learning with a very limited number of examples.