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.

本研究利用深度半监督学习结合数据增强技术、基于一致性正则化和伪标记的方法，大量利用未标记数据进行 RF 指纹识别，并证明我们提出的半监督 RF 指纹识别方法是明显优于其他竞争方法的，且可以在充足的条件下近乎完全监督与学习性能一致。

基于一致性正则化的半监督射频指纹识别

Semi-Supervised RF Fingerprinting with Consistency-Based Regularization

Fifth generation (5G) network and beyond envision massive Internet of Things
(IoT) rollout to support disruptive applications such as extended reality (XR),
augmented/virtual reality (AR/VR), industrial automation, autonomous driving,
and smart everything which brings together massive and diverse IoT devices
occupying the radio frequency (RF) spectrum. Along with the spectrum crunch and
throughput challenges, such a massive scale of wireless devices exposes
unprecedented threat surfaces. RF fingerprinting is heralded as a candidate
technology that can be combined with cryptographic and zero-trust security
measures to ensure data privacy, confidentiality, and integrity in wireless
networks. Motivated by the relevance of this subject in the future
communication networks, in this work, we present a comprehensive survey of RF
fingerprinting approaches ranging from a traditional view to the most recent
deep learning (DL)-based algorithms. Existing surveys have mostly focused on a
constrained presentation of the wireless fingerprinting approaches, however,
many aspects remain untold. In this work, however, we mitigate this by
addressing every aspect - background on signal intelligence (SIGINT),
applications, relevant DL algorithms, systematic literature review of RF
fingerprinting techniques spanning the past two decades, discussion on
datasets, and potential research avenues - necessary to elucidate this topic to
the reader in an encyclopedic manner.

本文探讨了将 RF 指纹技术与密码学和零信任安全措施相结合以保障无线网络中数据隐私、机密性和完整性的可行性，并综述了 RF 指纹技术的历史、应用、相关的深度学习算法，并探讨了该领域未来的发展方向。

无线电频率指纹识别综述：传统方法、深度学习及开放挑战

A Comprehensive Survey on Radio Frequency (RF) Fingerprinting: Traditional Approaches, Deep Learning, and Open Challenges

This paper presents how to leak private information from a wireless signal
classifier by launching an over-the-air membership inference attack (MIA). As
machine learning (ML) algorithms are used to process wireless signals to make
decisions such as PHY-layer authentication, the training data characteristics
(e.g., device-level information) and the environment conditions (e.g., channel
information) under which the data is collected may leak to the ML model. As a
privacy threat, the adversary can use this leaked information to exploit
vulnerabilities of the ML model following an adversarial ML approach. In this
paper, the MIA is launched against a deep learning-based classifier that uses
waveform, device, and channel characteristics (power and phase shifts) in the
received signals for RF fingerprinting. By observing the spectrum, the
adversary builds first a surrogate classifier and then an inference model to
determine whether a signal of interest has been used in the training data of
the receiver (e.g., a service provider). The signal of interest can then be
associated with particular device and channel characteristics to launch
subsequent attacks. The probability of attack success is high (more than 88%
depending on waveform and channel conditions) in identifying signals of
interest (and potentially the device and channel information) used to build a
target classifier. These results show that wireless signal classifiers are
vulnerable to privacy threats due to the over-the-air information leakage of
their ML models

本文介绍了如何通过发动一种空中成员推理攻击（MIA）来从无线信号分类器泄露私人信息的。攻击者可以使用泄露的信息利用机器学习模型的漏洞，这证明了无线信号分类器容易成为隐私威胁