TP-Net: Training Privacy-Preserving Deep Neural Networks Under Side-Channel Power Attacks
Authors: Dr. Hui Hu, Jessa Gegax-Randazzo, Clay Carper
Project Lead: Dr. Hui Hu
Advisor: Dr. Mike Borowczak
Abstract: Recent studies have shown the internal structure of a deep neural network is easily inferred via side-channel power attacks in the training process. To address this pressing privacy issue, we propose TP-NET, a novel solution for training privacy-preserving deep neural networks under side-channel power attacks. The main idea of TP-NET is to introduce randomness into the internal structure of a deep neural network and the training process.
