随机选客户端可有效防御对比联邦学习中的梯度攻击
Random Client Selection on Contrastive Federated Learning for Tabular Data
- 通过随机选择参与方提升模型安全性
- 实验证明该策略显著降低梯度泄露风险
- 适合关注隐私保护的联邦学习系统开发者
垂直联邦学习（VFL）通过跨多方协作训练模型，实现隐私保护。然而，中间计算共享仍存在信息泄露风险。尽管对比联邦学习（CFL）通过表征学习缓解了部分隐私问题，但仍易受基于梯度的攻击影响。本文对CFL环境下的梯度攻击进行了全面实验分析，并评估了随机客户端选择作为防御策略的有效性。大量实验表明，随机客户端选择在对抗梯度攻击方面表现优异。研究结果为构建更安全的对比联邦学习系统提供了重要参考，推动了安全协同学习框架的发展。
原文摘要 · Abstract (English)
Vertical Federated Learning (VFL) has revolutionised collaborative machine learning by enabling privacy-preserving model training across multiple parties. However, it remains vulnerable to information leakage during intermediate computation sharing. While Contrastive Federated Learning (CFL) was introduced to mitigate these privacy concerns through representation learning, it still faces challenges from gradient-based attacks. This paper presents a comprehensive experimental analysis of gradient-based attacks in CFL environments and evaluates random client selection as a defensive strategy. Through extensive experimentation, we demonstrate that random client selection proves particularly effective in defending against gradient attacks in the CFL network. Our findings provide valuable insights for implementing robust security measures in contrastive federated learning systems, contributing to the development of more secure collaborative learning frameworks
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。