Sparsified Federated Learning With Spiking Neural Networks: Resistance Against Byzantine Attacks While Lowering Communication Traffics

Spiking Neural Networks (SNN), which offer exceptional energy efficiency for inference, and Federated Learning (FL), which offers privacy-preserving 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-SNN, both poses significant threats on model convergence and training times, still remains largely unexplored. In this paper, we first systematically evaluate the robustness of ANN and SNN in the FL context under four model-poisoning Byzantine attacks. We find that FL-SNN demonstrate better reliability than FL-ANN against most Byzantine attacks except MinMax. We then propose the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$Top-\kappa$</tex> sparsification approach for better robustness in FL-SNN and to reduce communication overhead. Using this simple compression method, we observe ~40% accuracy enhancement in FL-SNN training under the lethal MinMax attack, leading to FL-SNN being more robust than FL-ANN in all four model-poisoning Byzantine attacks. This study highlights the dual benefits of FL-SNN with <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$Top-\kappa$</tex> sparsification in significantly reduce energy consumption and provide better robustness to Byzantine attacks for edge AI applications.