No abstract

No abstract

Most prior works on deep learning-based wireless device classification using radio frequency (RF) data apply off-the-shelf deep neural network (DNN) models, which were matured mainly for domains like vision and language. However, wireless RF data possesses unique characteristics that differentiate it from these other domains. For instance, RF data encompasses intermingled time and frequency features that are dictated by the underlying hardware and protocol configurations. In addition, wireless RF communication signals exhibit cyclostationarity due to repeated patterns (PHY pilots, frame prefixes, etc.) that these signals inherently contain. In this paper, we begin by explaining and showing the unsuitability as well as limitations of existing DNN feature design approaches currently proposed to be used for wireless device classification. We then present novel feature design approaches that exploit the distinct structures of the RF communication signals and the spectrum emissions caused by transmitter hardware impairments to custom-make DNN models suitable for classifying wireless devices using RF signal data. Our proposed DNN feature designs substantially improve classification robustness in terms of scalability, accuracy, signature anti-cloning, and insensitivity to environment perturbations. We end the paper by presenting other feature design strategies that have great potentials for providing further performance improvements of the DNN-based wireless device classification, and discuss the open research challenges related to these proposed strategies.

Deep learning (DL)-based RF fingerprinting (RFFP) technology has emerged as a powerful physical-layer security mechanism, enabling device identification and authentication based on unique device-specific signatures that can be extracted from the received RF signals. However, DL-based RFFP methods face major challenges concerning their ability to adapt to domain (e.g., day/time, location, channel, etc.) changes and variability. This work proposes a novel IQ data representation and feature design, termed Double-Sided Envelope Power Spectrum or EPS, that is proven to overcome the domain adaptation problems significantly. By accurately capturing device hardware impairments while suppressing irrelevant domain information, EPS offers improved feature selection for DL models in RFFP. Experimental evaluations demonstrate its effectiveness, achieving over 99% testing accuracy in same-day/channel/location evaluations and 93% accuracy in cross-day evaluations, outperforming the traditional IQ representation. Additionally, EPS excels in cross-location evaluations, achieving a 95% accuracy. The proposed representation significantly enhances the robustness and generalizability of DL-based RFFP methods, thereby presenting a transformative solution to IQ data-based device fingerprinting.

Deep-learning-based device fingerprinting has recently been recognized as a key enabler for automated network access authentication. Its robustness to impersonation attacks due to the inherent difficulty of replicating physical features is what distinguishes it from conventional cryptographic solutions. Although device fingerprinting has shown promising performances, its sensitivity to changes in the network operating environment still poses a major limitation. This paper presents an experimental framework that aims to study and overcome the sensitivity of LoRa-enabled device fingerprinting to such changes. We first begin by describing RF datasets we collected using our LoRa-enabled wireless device testbed. We then propose a new fingerprinting technique that exploits out-of-band distortion information caused by hardware impairments to increase the fingerprinting accuracy. Finally, we experimentally study and analyze the sensitivity of LoRa RF fingerprinting to various network setting changes. Our results show that fingerprinting does relatively well when the learning models are trained and tested under the same settings. However, when trained and tested under different settings, these models exhibit moderate sensitivity to channel condition changes and severe sensitivity to protocol configuration and receiver hardware changes when IQ data is used as input. However, with FFT data is used as input, they perform poorly under any change.