Robust Spiking Neural Networks Against Adversarial Attacks

TL;DR

This paper introduces a novel method called Threshold Guarding Optimization (TGO) that significantly improves the robustness of Spiking Neural Networks against adversarial attacks by modifying neuron potentials and firing mechanisms.

Contribution

The study identifies threshold-neighboring neurons as key factors limiting SNN robustness and proposes TGO to enhance security against adversarial disturbances.

Findings

TGO increases SNN robustness in adversarial scenarios.

Neurons' membrane potentials are effectively moved away from thresholds.

Probabilistic firing reduces state-flipping under minor disturbances.

Abstract

Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing due to their bio-plausible and spike-driven characteristics. However, the robustness of SNNs in complex adversarial environments remains significantly constrained. In this study, we theoretically demonstrate that those threshold-neighboring spiking neurons are the key factors limiting the robustness of directly trained SNNs. We find that these neurons set the upper limits for the maximum potential strength of adversarial attacks and are prone to state-flipping under minor disturbances. To address this challenge, we propose a Threshold Guarding Optimization (TGO) method, which comprises two key aspects. First, we incorporate additional constraints into the loss function to move neurons' membrane potentials away from their thresholds. It increases SNNs' gradient sparsity, thereby reducing the theoretical upper bound of adversarial attacks. Second, we introduce noisy spiking neurons to transition the neuronal firing mechanism from deterministic to probabilistic, decreasing their state-flipping probability due to minor disturbances. Extensive experiments conducted in standard adversarial scenarios prove that our method significantly enhances the robustness of directly trained SNNs. These findings pave the way for advancing more reliable and secure neuromorphic computing in real-world applications.