On the Sensitivity of Firing Rate-Based Federated Spiking Neural Networks to Differential Privacy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911443158302720 |
|---|---|
| author | Pereira, Luiz Perkusich, Mirko Valadares, Dalton Gorgônio, Kyller |
| author_facet | Pereira, Luiz Perkusich, Mirko Valadares, Dalton Gorgônio, Kyller |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12009 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On the Sensitivity of Firing Rate-Based Federated Spiking Neural Networks to Differential Privacy Pereira, Luiz Perkusich, Mirko Valadares, Dalton Gorgônio, Kyller Machine Learning Artificial Intelligence 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. |
| title | On the Sensitivity of Firing Rate-Based Federated Spiking Neural Networks to Differential Privacy |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.12009 |