FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intelligent Devices

2026-08-02

AI Summary

Federated learning is vulnerable to Byzantine attacks, and existing defenses rely on strong assumptions—such as the proportion of malicious clients being below 50% or the server possessing a task-relevant root dataset—and struggle with benign update heterogeneity and the curse of dimensionality in high-dimensional updates. To address these limitations, this work proposes FL-OA, a novel framework that introduces an external third party holding a root dataset to perform outsourced auditing, thereby eliminating reliance on conventional strong assumptions. FL-OA reduces divergence among benign updates by incorporating gradient ascent and correction terms during local training and designs a parameter importance metric to identify critical parameters for efficient dimensionality reduction in auditing. Theoretical analysis and extensive experiments demonstrate that FL-OA significantly outperforms existing methods across diverse attack scenarios, achieving both robustness and practicality.

Abstract

Federated learning (FL) enables multiple intelligent devices to collaboratively train a high-accuracy model without sharing raw data. However, due to its distributed nature, FL is vulnerable to Byzantine attacks. Existing defense methods rely on strong assumptions, such as the proportion of malicious devices not exceeding 50\%, or the server having an additional root dataset that matches the training task. Moreover, they show limited efficacy as they overlook $(i)$ the divergence among benign updates and $(ii)$ the curse of dimensionality involved in comparing two high-dimensional updates. To solve these concerns, we propose FL-OA, a Byzantine-robust federated learning framework utilizing outsourced auditing. In FL-OA, the server collaborates with third-party organization that holds an additional root dataset to perform outsourced auditing, thereby enabling the server to achieve robust aggregation without strong assumptions. Additionally, FL-OA introduces a gradient ascent step and a correction term during local training to mitigate the divergence among benign updates, and designs a parameter importance indicator to extract critical parameters for auditing, alleviating the curse of dimensionality. We further provide a detailed theoretical analysis of FL-OA. Extensive experiments demonstrate that FL-OA outperforms existing defense methods against Byzantine attacks.

Problem

• Byzantine attacks
• federated learning
• outsourced auditing
• dimensionality curse
• benign update divergence

Innovation

• Byzantine-robust
• outsourced auditing
• federated learning
• parameter importance
• gradient correction