English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Wireless device classification techniques play a key role in promotingemerging wireless applications such as allowing spectrum regulatory agencies toenforce their access policies and enabling network administrators to controlaccess and prevent impersonation attacks to their wireless networks. Leveragingspectrum distortions of transmitted RF signals, caused by transceiver hardwareimpairments created during manufacture and assembly stages, to provide deviceclassification has been the focus of many recent works. These prior worksessentially apply deep learning to extract features of the devices from theirhardware-impaired signals and rely on feature variations across the devices todistinguish devices from one another. As technology advances, the manufacturingimpairment variations across devices are becoming extremely insignificant,making these prior classification approaches inaccurate. This paper proposes anovel, deep learning-based technique that provides scalable and highly accurateclassification of wireless devices, even when the devices exhibit insignificantvariation across their hardware impairments and have the same hardware,protocol, and software configurations. The novelty of the proposed techniquelies in leveraging both the {\em in-band} and {\em out-of-band} signaldistortion information by oversampling the captured signals at the receiver andfeeding IQ samples collected from the RF signals to a deep neural network forclassification. Using a convolutional neural network (CNN) model, we show thatour proposed technique, when applied to high-end, high-performance devices withminimally distorted hardware, doubles the device classification accuracy whencompared to existing approaches.

Leveraging Hardware-Impaired Out-of-Band Information Through Deep Neural Networks for Robust Wireless Device Classification