The Robustness of Spiking Neural Networks in Federated Learning with Compression Against Non-omniscient Byzantine Attacks

TL;DR

This paper demonstrates that integrating Top-kappa sparsification into federated learning with spiking neural networks enhances robustness against Byzantine attacks and reduces communication bandwidth, leading to significant accuracy improvements.

Contribution

It introduces a simple method combining Top-kappa sparsification with FL-SNNs to improve robustness and efficiency against non-omniscient Byzantine attacks.

Findings

40% accuracy gain under MinMax attack

Reduced bandwidth usage through sparsification

Enhanced robustness of FL-SNNs compared to FL-ANNs

Abstract

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