RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing Coding

TL;DR

This paper introduces RSC-SNN, a method that leverages Poisson coding and randomized smoothing to enhance the adversarial robustness of Spiking Neural Networks, achieving state-of-the-art results on large-scale datasets like ImageNet.

Contribution

It provides a theoretical analysis linking Poisson coding to adversarial robustness and proposes RSC as a novel approach to improve SNN robustness on large datasets.

Findings

RSC-SNN outperforms previous models in adversarial robustness.

Poisson coding is theoretically linked to randomized smoothing.

Achieves state-of-the-art robustness on ImageNet.

Abstract

Spiking Neural Networks (SNNs) have received widespread attention due to their unique neuronal dynamics and low-power nature. Previous research empirically shows that SNNs with Poisson coding are more robust than Artificial Neural Networks (ANNs) on small-scale datasets. However, it is still unclear in theory how the adversarial robustness of SNNs is derived, and whether SNNs can still maintain its adversarial robustness advantage on large-scale dataset tasks. This work theoretically demonstrates that SNN's inherent adversarial robustness stems from its Poisson coding. We reveal the conceptual equivalence of Poisson coding and randomized smoothing in defense strategies, and analyze in depth the trade-off between accuracy and adversarial robustness in SNNs via the proposed Randomized Smoothing Coding (RSC) method. Experiments demonstrate that the proposed RSC-SNNs show remarkable adversarial robustness, surpassing ANNs and achieving state-of-the-art robustness results on large-scale dataset ImageNet. Our open-source implementation code is available at this https URL: https://github.com/KemingWu/RSC-SNN.