Machine Learning for RF Information Leakage Characterization in Low Cost Bluetooth Implementation
Dr. Joshi, Department of Computer Science and Engineering
Due to tight on-die integration in low-cost, low-power wireless modules, digital and mixed-signal subsystems are often placed very close to each other. Noise coupling from the digital system is often indicative of the computations being performed and thus leaks information to the outside world. We would like to characterize this leakage and see what can we infer about the computations occurring inside the chip using only the signals leaking outside.
The student will be conducting in-lab experiments with commercial bluetooth development boards, the student will be working with software-defined radio kits to record this information. The student will then learn how to use modern machine learning tools to automate the process of information extraction and capture.