Mitigating Sybils in Federated Learning Poisoning-猫眼课题宝

DOI：

发表时间：

2018-08

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Clement Fung;Chris J. M. Yoon;Ivan Beschastnikh

分布式多方数据上的机器学习（ML）是各种领域所需要的。现有的方法，如联合学习，收集由一组设备在中央聚合器计算的输出，并运行迭代算法来训练全局共享模型。不幸的是，这种方法容易受到各种攻击，包括模型中毒，这在sybil的存在下变得更糟。在本文中，我们首先评估了联邦学习对基于sybil的中毒攻击的脆弱性。然后，我们描述了一个新的防御这个问题，确定中毒sybils的基础上的客户端更新的多样性，在分布式学习过程中。与以前的工作不同，我们的系统不限制预期的攻击者数量，不需要学习过程之外的辅助信息，并且对客户端及其数据的假设较少。在我们的评估中，我们表明FoolsGold超过了现有最先进的方法来对抗基于sybil的标签翻转和后门中毒攻击的能力。我们的研究结果适用于不同分布的客户端数据，不同的中毒目标，和各种sybil策略。代码可以在以下位置找到：此https URL

Machine learning (ML) over distributed multi-party data is required for a variety of domains. Existing approaches, such as federated learning, collect the outputs computed by a group of devices at a central aggregator and run iterative algorithms to train a globally shared model. Unfortunately, such approaches are susceptible to a variety of attacks, including model poisoning, which is made substantially worse in the presence of sybils. In this paper we first evaluate the vulnerability of federated learning to sybil-based poisoning attacks. We then describe \emph{FoolsGold}, a novel defense to this problem that identifies poisoning sybils based on the diversity of client updates in the distributed learning process. Unlike prior work, our system does not bound the expected number of attackers, requires no auxiliary information outside of the learning process, and makes fewer assumptions about clients and their data. In our evaluation we show that FoolsGold exceeds the capabilities of existing state of the art approaches to countering sybil-based label-flipping and backdoor poisoning attacks. Our results hold for different distributions of client data, varying poisoning targets, and various sybil strategies. Code can be found at: this https URL

Mitigating Sybils in Federated Learning Poisoning

文献摘要

被引文献

相似文献