This study examines the impact of additive and multiplicative noise on both a single leaky integrate-and-fire (LIF) neuron and a trained spiking neural network (SNN). Noise was introduced at different stages of neural processing, including the input current, membrane potential, and output spike generation. The results show that multiplicative noise applied to the membrane potential has the most detrimental effect on network performance, leading to a significant degradation in accuracy. This is primarily due to its tendency to suppress membrane potentials toward large negative values, effectively silencing neuronal activity. To address this issue, input pre-filtering strategies were evaluated, with a sigmoid-based filter demonstrating the best performance by shifting inputs to a strictly positive range. Under these conditions, additive noise in the input current becomes the dominant source of performance degradation, while other noise configurations reduce accuracy by no more than 1\%, even at high noise intensity. Additionally, the study compares the effects of common and uncommon noise across neuron populations in hidden layer, revealing that SNNs exhibit greater robustness to common noise. Overall, the findings identify the most critical noise mechanisms affecting SNNs and provide practical approaches for improving their robustness.

翻译：本研究探究了加性噪声和乘性噪声对单个泄漏积分-触发（LIF）神经元及训练好的脉冲神经网络（SNN）的影响。噪声被引入神经处理的不同阶段，包括输入电流、膜电位和输出脉冲生成。结果表明，施加于膜电位的乘性噪声对网络性能的破坏性最大，导致准确率显著下降，其主要原因在于该噪声倾向于将膜电位抑制至较大负值，从而有效沉默神经元活动。为解决该问题，本文评估了输入预滤波策略，其中基于S形函数的滤波器通过将输入限定在严格正值范围内展现出最优性能。在此条件下，输入电流中的加性噪声成为性能退化的主导因素，而其他噪声配置即使在极高噪声强度下也仅使准确率降低不超过1%。此外，研究对比了隐藏层神经元群体中常见噪声与非常见噪声的影响，发现SNN对常见噪声具有更强的鲁棒性。总体而言，本研究确定了影响SNN的最关键噪声机制，并提供了增强其鲁棒性的实用方法。