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

2025-01-06

AI Summary

Federated learning (FL) in IoT faces dual challenges of omniscient-agnostic Byzantine attacks and severe bandwidth constraints. Method: This paper pioneers a systematic investigation into the synergistic advantages of spiking neural networks (SNNs) over artificial neural networks (ANNs) in terms of both adversarial robustness and communication efficiency. We propose a novel paradigm integrating Top-κ gradient sparsification with the intrinsic sparse spike-based activation of SNNs, jointly optimizing model update compression and malicious client filtering. Contribution/Results: Under omniscient-agnostic Byzantine attacks (e.g., MinMax), FL-SNN achieves ~40% higher accuracy than baseline FL methods, significantly reduces communication overhead, accelerates convergence, and enhances robustness. This work establishes a verifiable framework and new design principles for secure, efficient edge intelligence in resource-constrained, highly adversarial IoT environments.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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

Problem

• Pulse Neural Networks (SNNs)
• Federated Learning (FL)
• Byzantine Attacks and Bandwidth Constraints

Innovation

• Spiking Neural Networks (SNNs)
• Top-kappa Sparsification
• Byzantine Robustness