The Robustness of Spiking Neural Networks in Federated Learning with Compression Against Non-omniscient Byzantine Attacks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929663080660992 |
|---|---|
| author | Nguyen, Manh V. Zhao, Liang Deng, Bobin Wu, Shaoen |
| author_facet | Nguyen, Manh V. Zhao, Liang Deng, Bobin Wu, Shaoen |
| contents | Spiking Neural Networks (SNNs), which offer exceptional energy efficiency for inference, and Federated Learning (FL), which offers privacy-preserving distributed training, is a rising area of interest that highly beneficial towards Internet of Things (IoT) devices. Despite this, research that tackles Byzantine attacks and bandwidth limitation in FL-SNNs, both poses significant threats on model convergence and training times, still remains largely unexplored. Going beyond proposing a solution for both of these problems, in this work we highlight the dual benefits of FL-SNNs, against non-omniscient Byzantine adversaries (ones that restrict attackers access to local clients datasets), and greater communication efficiency, over FL-ANNs. Specifically, we discovered that a simple integration of Top-\k{appa} sparsification into the FL apparatus can help leverage the advantages of the SNN models in both greatly reducing bandwidth usage and significantly boosting the robustness of FL training against non-omniscient Byzantine adversaries. Most notably, we saw a massive improvement of roughly 40% accuracy gain in FL-SNNs training under the lethal MinMax attack |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03306 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Robustness of Spiking Neural Networks in Federated Learning with Compression Against Non-omniscient Byzantine Attacks Nguyen, Manh V. Zhao, Liang Deng, Bobin Wu, Shaoen Cryptography and Security Distributed, Parallel, and Cluster Computing Machine Learning Spiking Neural Networks (SNNs), which offer exceptional energy efficiency for inference, and Federated Learning (FL), which offers privacy-preserving distributed training, is a rising area of interest that highly beneficial towards Internet of Things (IoT) devices. Despite this, research that tackles Byzantine attacks and bandwidth limitation in FL-SNNs, both poses significant threats on model convergence and training times, still remains largely unexplored. Going beyond proposing a solution for both of these problems, in this work we highlight the dual benefits of FL-SNNs, against non-omniscient Byzantine adversaries (ones that restrict attackers access to local clients datasets), and greater communication efficiency, over FL-ANNs. Specifically, we discovered that a simple integration of Top-\k{appa} sparsification into the FL apparatus can help leverage the advantages of the SNN models in both greatly reducing bandwidth usage and significantly boosting the robustness of FL training against non-omniscient Byzantine adversaries. Most notably, we saw a massive improvement of roughly 40% accuracy gain in FL-SNNs training under the lethal MinMax attack |
| title | The Robustness of Spiking Neural Networks in Federated Learning with Compression Against Non-omniscient Byzantine Attacks |
| topic | Cryptography and Security Distributed, Parallel, and Cluster Computing Machine Learning |
| url | https://arxiv.org/abs/2501.03306 |