PrivateSNN: Privacy-Preserving Spiking Neural Networks

TL;DR

PrivateSNN introduces a privacy-preserving, energy-efficient spiking neural network approach that encrypts weights and uses synthetic data to prevent data and class leakage during conversion from pre-trained ANNs.

Contribution

The paper proposes a novel method to build privacy-preserving SNNs from ANNs by encrypting weights and using synthetic data, reducing leakage risks and maintaining high energy efficiency.

Findings

Eliminates data and class leakage with less than 2% performance drop.

Achieves approximately 55x energy efficiency gain over standard ANNs.

Effective on datasets like CIFAR10, CIFAR100, and TinyImageNet.

Abstract

How can we bring both privacy and energy-efficiency to a neural system? 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 is caused when the networks access real training data during an ANN-SNN conversion process. 2) Class leakage is 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 the generated images. However, converted SNNs remain vulnerable to 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 SNNs difficult to be interpreted in the spatial domain. We observe that the encrypted PrivateSNN eliminates data and class leakage issues with a slight performance drop (less than ~2) and significant energy-efficiency gain (about 55x) 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.