基于时序互信息的鲁棒脉冲神经网络
Robust Spiking Neural Networks by Temporal Mutual Information
把信息瓶颈推广到时序维度，用输入与脉冲潜变量之间的互信息作为正则项来收紧鲁棒误差界；做脉冲网络或时序动态模型对抗鲁棒性的人可以直接复用这一正则化思路与理论分析框架。
原文依据 we propose a Temporal Mutual Information (TMI) regularizer that explicitly exploits temporal characteristics to enhance robustness
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论脉冲神经网络（SNN）因其受生物启发的时序动力学而受到越来越多的关注。随着其应用范围的扩大，理解其鲁棒性已成为重要的研究焦点。然而，关于 SNN 内在的时序特性如何影响鲁棒性，目前仍知之甚少。在本工作中，我们从信息论视角重新审视 SNN 的鲁棒性，并揭示了时序动力学的关键作用。基于信息瓶颈原理，我们建立了鲁棒性误差与输入和潜变量表示之间沿时序维度的互信息（MI）之间的理论联系。通过对基于脉冲的信息传递进行分析，我们表明时序动力学本质上会压缩互信息，从而收紧鲁棒性误差界。基于这一洞见，我们提出了一种时序互信息（TMI）正则化器，显式利用时序特性来增强鲁棒性。在 CIFAR-10、CIFAR-100、DVS-CIFAR10、Tiny-ImageNet 和 ImageNet 上的大量实验表明，我们的方法在各种架构和攻击设置下都能持续提升 SNN 的鲁棒性。
英文原文摘要 1180 字符
Spiking Neural Networks (SNNs) have attracted increasing attention for their biologically inspired temporal dynamics. As their applications expand, understanding their robustness has become an important research focus. However, little is known about how the intrinsic temporal properties of SNNs affect robustness. In this work, we revisit SNN robustness from an information-theoretic perspective and reveal the pivotal role of temporal dynamics. We establish a theoretical link between robustness error and the mutual information (MI) between inputs and latent representations along the temporal dimension, grounded in the information bottleneck principle. Through an analysis of spike-based information transmission, we show that temporal dynamics inherently compress MI, thereby tightening the robustness error bound. Building on this insight, we propose a Temporal Mutual Information (TMI) regularizer that explicitly exploits temporal characteristics to enhance robustness. Extensive experiments on CIFAR-10, CIFAR-100, DVS-CIFAR10, Tiny-ImageNet, and ImageNet demonstrate that our method consistently improves SNN robustness across various architectures and attack settings.