Radio Frequency (RF) Fingerprinting of LoRaWAN Transmissions

There is an ever-increasing use of low-power wireless sensor technology, for example LoRaWAN, for sensing and monitoring applications, thus identifying a need to make this technology robust against cyber attacks. This is one of the use-cases being considered by the UKRI/EPSRC Prosperity Partnership in Secure Wireless Agile Networks (SWAN). SWAN is addressing radio frequency (RF) based cyber attack detection and mitigation, rather than network orientated intrusion.
Within SWAN we have developed an RF penetration test-bed (pen-test) to facilitate both the injection of jamming waveforms as well as extraction live over-the-air (OTA) waveforms for RF fingerprinting, with LoRa as a first candidate technology. In the virtual demo, we will show a two-pronged methodology for RF finger printing of the start-up chirps from a LoRa modem. Firstly, a self-organising feature map (SOFM) is trained using unsupervised competitive learning of neural network (NN) clusters to produce two-dimensional (2D) discretised representations of the input space. The input space consists of the differential constellation trace of LoRa I/Q samples. These I/Q samples are extracted from LoRa RF transmissions form different LoRa transceiver modules (RN2483 from Microchip); as well as a baseband LoRa waveform that is generated in MATLAB, then up converted and transmitted using a vector signal generator (VSG). Secondly, an optimised deep convolutional neural network (CNN) architecture with batch normalisation at every convolutional layer is proposed. The CNN is trained using labelled datasets compiled from the 2D SOFMs from multiple training epochs of the original NN clusters. The proposed architecture is expected to be invariant medium access control (MAC) ID spoofing. In other words, it learns only physical (PHY) layer features due to the differential constellation trace of LoRa I/Qs without learning the MAC features. Our current work demonstrates cent-percent accuracy. Further research challenges for increasing the robustness of this approach by adding additive white Gaussian noise (AWGN) and channel impairments for the emulation of OTA transmission are discussed.