PrivateSNN: Fully Privacy-Preserving Spiking Neural Networks

How can we bring both privacy and energy-efficiency to a neural system on edge devices? In this paper, we propose PrivateSNN, which aims to build low-power Spiking Neural Networks (SNNs) from a pre-trained ANN model without leaking sensitive information contained in a dataset. Here, we tackle two types of leakage problems: 1) Data leakage caused when the networks access real training data during an ANN-SNN conversion process. 2) Class leakage is the concept of leakage caused when class-related features can be reconstructed from network parameters. In order to address the data leakage issue, we generate synthetic images from the pre-trained ANNs and convert ANNs to SNNs using generated images. However, converted SNNs are still vulnerable with respect to the class leakage since the weight parameters have the same (or scaled) value with respect to ANN parameters. Therefore, we encrypt SNN weights by training SNNs with a temporal spike-based learning rule. Updating weight parameters with temporal data makes networks difficult to be interpreted in the spatial domain. We observe that the encrypted PrivateSNN can be implemented not only without the huge performance drop (less than ~5%) but also with significant energy-efficiency gain (about x60 compared to the standard ANN). We conduct extensive experiments on various datasets including CIFAR10, CIFAR100, and TinyImageNet, highlighting the importance of privacy-preserving SNN training.