Details
Poster
Presenter(s)
![Bo Li Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/20721.jpg?h=df1b6c88&itok=82uO5KMU)
Display Name
Bo Li
- Affiliation
-
AffiliationMacquarie University
- Country
Abstract
With increasing popularity of deep learning Radio Frequency (RF) fingerprinting approaches have attracted attention with new techniques proposed. In this paper we present a novel waveform domain-based approach operating on images generated from captured raw samples for device identification. The use of images enables the capture of information from theoretically infinite number of raw samples without impacting the structure and the complexity of the subsequent deep learning processing. The efficacy of the proposed approach is demonstrated using over-the-air signals captured from 12 Zigbee devices, with the proposed approach achieving near 99% identification accuracy.