研究隐私保护下神经脉冲网络的放电率敏感性，揭示差分隐私如何影响协作训练。
On the Sensitivity of Firing Rate-Based Federated Spiking Neural Networks to Differential Privacy
- 通过梯度裁剪和噪声注入扰动脉冲网络放电率统计
- 发现隐私预算越小，放电率偏移越明显，聚合效果下降
- 适合关注边缘设备隐私计算的开发者与研究人员
联邦类脑学习（FNL）可在不集中数据的情况下实现节能且隐私保护的学习。然而，真实场景部署需引入额外隐私机制，可能显著改变训练信号。本文分析差分隐私（DP）机制（尤其是梯度裁剪与噪声注入）如何扰动脉冲神经网络（SNNs）的放电率统计，并影响基于放电率的联邦协调过程。在非独立同分布（non-IID）设置下的语音识别任务中，对不同隐私预算和裁剪阈值的消融实验显示：存在系统性放电率偏移、聚合性能衰减以及客户端选择中的排序不稳定现象。此外，我们发现这些偏移与稀疏性和记忆指标相关。研究结果为隐私保护的联邦类脑学习提供了可操作指导，尤其关于隐私强度与依赖放电率的协调之间的权衡。
原文摘要 · Abstract (English)
Federated Neuromorphic Learning (FNL) enables energy-efficient and privacy-preserving learning on devices without centralizing data. However, real-world deployments require additional privacy mechanisms that can significantly alter training signals. This paper analyzes how Differential Privacy (DP) mechanisms, specifically gradient clipping and noise injection, perturb firing-rate statistics in Spiking Neural Networks (SNNs) and how these perturbations are propagated to rate-based FNL coordination. On a speech recognition task under non-IID settings, ablations across privacy budgets and clipping bounds reveal systematic rate shifts, attenuated aggregation, and ranking instability during client selection. Moreover, we relate these shifts to sparsity and memory indicators. Our findings provide actionable guidance for privacy-preserving FNL, specifically regarding the balance between privacy strength and rate-dependent coordination.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。