mlsanityData to 14 Oct 2026

On the Sensitivity of Firing Rate-Based Federated Spiking Neural Networks to Differential Privacy

arXiv 2602.12009 ↗First posted 12 Feb 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 19 references that are in the map. First posted on arXiv 12 Feb 2026.

Builds on

12 of 19 references.

References · 12

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2018How To Backdoor Federated Learningcited by 765
  4. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  5. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 259
  6. 2021Numerical Composition of Differential Privacycited by 180
  7. 2021Federated Learning with Spiking Neural Networkscited by 23
  8. 2019Federated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligencecited by 16
  9. 2025DA-LIF: Dual Adaptive Leaky Integrate-and-Fire Model for Deep Spiking Neural Networkscited by 8
  10. 2025Federated Learning: A Survey on Privacy-Preserving Collaborative Intelligencecited by 4
  11. 2024SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learningcited by 2
  12. 2024The Robustness of Spiking Neural Networks in Communication and its Application towards Network Efficiency in Federated Learningcited by 1

Built on by

Not cited yet.