通过一致性评分提升联邦学习抗恶意攻击能力
Embedding Byzantine Fault Tolerance into Federated Learning via Consistency Scoring
- 用虚拟数据生成评估本地更新的一致性，过滤异常参数
- 30%定向攻击下准确率超89.6%，无防护时仅19.5%
- 可无缝集成现有方法，适合高安全需求的边缘场景
在多个边缘设备提供充足数据的前提下，联邦学习（FL）可在不传输私有数据的情况下训练共享模型。然而，FL通常易受被攻陷设备发起的拜占庭攻击影响，严重降低模型性能。本文提出一种直观的插件机制，可无缝嵌入现有联邦学习方法以实现拜占庭容错。核心思想是生成虚拟数据样本，并通过评估本地更新间的一致性得分，有效过滤受损更新。该评分机制在聚合前执行，使原有FL方法具备抗拜占庭攻击能力，同时保留其原有优势。血细胞分类任务的数值结果表明，该插件显著提升系统鲁棒性：附加插件的FedAvg在30%定向攻击下测试准确率达89.6%（无插件时仅19.5%），在非定向攻击下仍保持65-70%准确率（无插件时为17-19%）。
原文摘要 · Abstract (English)
Given sufficient data from multiple edge devices, federated learning (FL) enables training a shared model without transmitting private data to the central server. However, FL is generally vulnerable to Byzantine attacks from compromised edge devices, which can significantly degrade the model performance. In this work, we propose an intuitive plugin that seamlessly embeds Byzantine resilience into existing FL methods. The key idea is to generate virtual data samples and evaluate model consistency scores across local updates to effectively filter out compromised updates. By utilizing this scoring mechanism before the aggregation phase, the proposed plugin enables existing FL methods to become robust against Byzantine attacks while maintaining their original benefits. Numerical results on blood cell classification task demonstrate that the proposed plugin provides strong Byzantine resilience. In detail, plugin-attached FedAvg achieves over 89.6% test accuracy under 30% targeted attacks (vs.19.5% w/o plugin) and maintains 65-70% test accuracy under untargeted attacks (vs.17-19% w/o plugin).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。