RF Transmitter Fingerprinting Exploiting Spatio-Temporal Properties in Raw Signal Data

The recent advances of wireless technologies in RF environments coupled with large scale usage of such technologies has warranted more autonomous deployments of wireless systems. Machine learning techniques, that include recurrent structures, have shown promise in creating such autonomous deployments using the idea of Radio Frequency Machine Learning (RFML). In large scale autonomous deployments of wireless communication networks, the signals received from one component play a crucial role in the decision making process of other components. In order to efficiently implement such systems each component of the network should be uniquely identifiable. In this paper we propose a transmitter fingerprinting technique for radio device identification using recurrent structures, by exploiting the temporal property of the received radio signal. We design and implement three recurrent neural networks (RNNs) using different types of cell models: (i) long short term memory (LSTM); (ii) gated recurrent unit (GRU) and (iii) convolutional long short term memory (ConvLSTM), for this task. We program 8 universal software radio peripheral (USRP) software defined radios (SDRs) as transmitters and collect over-the-air raw in-phase (I) and quadrature (Q) (I/Q) time series data from them using a DVB-T RTL-SDR receiver, in a laboratory setting. We exploit both the temporal variations as well as the inherent spatial dependencies in the collected I/Q time series data, to learn unique feature representations and use these as "fingerprints'" for identifying the transmitters. Experimental results reveal that the RNNs with LSTM, GRU, and ConvLSTM cells are able to correctly distinguish between the 8 transmitters with 92%, 95.3%, 97.2% accuracy respectively.