arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.22149cs.LGcs.AIcs.CLcs.CRcs.CVcs.DC
收藏

赋予客户端权力:在独裁者设定下的联邦学习

Power to the Clients: Federated Learning in a Dictatorship Setting

Department of Computer Science, Rensselaer Polytechnic Institute(拉特格斯理工学院计算机科学系)

Mohammadsajad Alipour, Mohammad Mohammadi Amiri

AI总结:

本文研究了联邦学习中恶意客户端对模型收敛的影响,提出独裁者客户端概念并分析其攻击策略,通过理论与实验验证多客户端协作、独立或联盟等复杂场景下的学习效果。

摘要:

联邦学习(FL)作为一种去中心化的模型训练范式,使多个客户端能够协同学习共享模型而无需交换本地数据。然而,FL的去中心化特性也引入了安全风险,恶意客户端可能破坏或操控训练过程。本文引入了独裁者客户端,一种新型、明确且可分析的恶意参与者,其能够完全擦除其他客户端对服务器模型的贡献,同时保留自身贡献。我们提出了具体的攻击策略,系统分析了这些客户端对学习过程的影响。此外,我们探索了涉及多个独裁者客户端的复杂场景,包括他们协作、独立行动或形成联盟以最终背叛彼此的情况。对于每种设置,我们提供了对全局模型收敛影响的理论分析。我们的理论算法和关于多独裁者客户端复杂场景的发现进一步通过计算机视觉和自然语言处理基准的实证评估得到支持。

英文摘要:

Federated learning (FL) has emerged as a promising paradigm for decentralized model training, enabling multiple clients to collaboratively learn a shared model without exchanging their local data. However, the decentralized nature of FL also introduces vulnerabilities, as malicious clients can compromise or manipulate the training process. In this work, we introduce dictator clients, a novel, well-defined, and analytically tractable class of malicious participants capable of entirely erasing the contributions of all other clients from the server model, while preserving their own. We propose concrete attack strategies that empower such clients and systematically analyze their effects on the learning process. Furthermore, we explore complex scenarios involving multiple dictator clients, including cases where they collaborate, act independently, or form an alliance in order to ultimately betray one another. For each of these settings, we provide a theoretical analysis of their impact on the global model's convergence. Our theoretical algorithms and findings about the complex scenarios including multiple dictator clients are further supported by empirical evaluations on both computer vision and natural language processing benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑