RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing Coding
This addresses the adversarial robustness challenge for Spiking Neural Networks on large-scale datasets, providing theoretical insights and a practical method.
This work theoretically demonstrates that Spiking Neural Networks' adversarial robustness stems from Poisson coding, revealing its equivalence to randomized smoothing defense strategies, and proposes Randomized Smoothing Coding (RSC) to explore the accuracy-robustness trade-off. Experiments show RSC-SNNs achieve state-of-the-art robustness on ImageNet, surpassing Artificial Neural Networks.
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.