DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Pooling

TL;DR

This paper introduces DPSNN, a differentially private spiking neural network that combines DP with SNNs and employs a novel temporal enhanced pooling method to preserve privacy without sacrificing performance.

Contribution

It proposes a novel DPSNN model integrating differential privacy with SNNs and introduces TEP to enhance information transfer and maintain high accuracy.

Findings

Maintains high performance with strong privacy protection.

Effective on static and neuromorphic datasets.

Temporal enhanced pooling improves information transfer.

Abstract

Privacy protection is a crucial issue in machine learning algorithms, and the current privacy protection is combined with traditional artificial neural networks based on real values. Spiking neural network (SNN), the new generation of artificial neural networks, plays a crucial role in many fields. Therefore, research on the privacy protection of SNN is urgently needed. This paper combines the differential privacy(DP) algorithm with SNN and proposes a differentially private spiking neural network (DPSNN). The SNN uses discrete spike sequences to transmit information, combined with the gradient noise introduced by DP so that SNN maintains strong privacy protection. At the same time, to make SNN maintain high performance while obtaining high privacy protection, we propose the temporal enhanced pooling (TEP) method. It fully integrates the temporal information of SNN into the spatial information transfer, which enables SNN to perform better information transfer. We conduct experiments on static and neuromorphic datasets, and the experimental results show that our algorithm still maintains high performance while providing strong privacy protection.