Privacy Preserving Radio Frequency Fingerprinting via Jamming

This thesis presents a comprehensive investigation into the preservation of signal quality against various levels of jamming interference, critically examining the dynamic interaction between maintaining signal integrity and counteracting deliberate disruption attempts. At the heart of this research lies the innovative application of deep learning models, which have demonstrated a significant capacity to adapt to and mitigate the destructive impacts of jamming, thus improving the reliability of communication networks under jamming conditions. A novel approach to visual analysis was employed, showcasing the robustness of select neural network architectures by visualizing in-phase and quadrature signal components. Future endeavors are focused on utilizing the acquired insights to significantly strengthen communication infrastructures and preserve precise signal transmission despite sophisticated jamming levels and techniques. As a significant contribution to the field of communications and signal processing, this body of work clears the path toward a future where signal integrity is ensured, opening the door for developing more secure, reliable, and robust communication channels in an era of increasing interference threats.