In this thesis, we describe a method for uniquely identifying a specific radio among nominally similar devices using a combination of SDR sensing capability and machine learning (ML) techniques. Our approach of radio fingerprinting applies ML over raw I/Q samples without specifically selecting features of interest. It distinguishes devices using only the transmitter hardware-induced signal modifications that serve as a unique signature for a particular device. No higher level decoding, feature engineering, or protocol knowledge is needed, further mitigating challenges of ID spoofing and coexistence of multiple protocols in a shared spectrum.
Advances in software defined radio (SDR) technology allows unprecedented control on the entire processing chain, allowing modification of each functional block as well as sampling the changes in the input waveform. We first demonstrate RF impairments by modifying the operational blocks in a typical wireless communications processing chain in a simulation study. We then generate over-the-air dataset compiled from an experimental testbed of SDRs such as B210 and X310 and train the data using an optimized deep convolutional neural network (CNN) architecture that gives good classification accuracy. We describe the parallel processing needs and choice of several hyper parameters to enable efficient training of the CNN model. We then compare the performance quantitatively with alternate techniques such as support vector machines and logistic regression. Overall our results show that we can achieve up to 90-99\% experimental accuracy at transmitter-receiver distances varying between 2-50 feet over a noisy, multi-path wireless channel.
- Professor Kaushik Chowdhury (Advisor)
- Professor Stratis Ioannidis
- Professor Aatmesh Shrivastava