arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.07704cs.LGcs.CRcs.DC
收藏

Simeon --通过迭代过滤实现安全的联邦机器学习

Simeon -- Secure Federated Machine Learning Through Iterative Filtering

School of Computer Science and Engineering, University of New South Wales(新南威尔士大学计算机科学与工程学院);Department of Computer Science, Purdue University(普渡大学计算机科学系)

Nicholas Malecki, Hye-young Paik, Aleksandar Ignjatovic, Alan Blair, Elisa Bertino

摘要:

联邦学习使得全局机器学习模型能够由分布式的、相互不信任的学习代理协作地训练,这些学习代理希望维护其训练数据和其硬件的隐私。一个全局模型被分发给客户端,客户端执行训练,并提交他们新训练的模型,以聚合成一个更好的模型。然而,联邦学习系统容易受到恶意学习代理的干扰,这些恶意学习代理可能希望阻止训练或在最终的全局模型中引起有针对性的错误分类。已经出现了一类容忍拜占庭的聚合算法,提供了不同程度的鲁棒性来对抗这些攻击,通常需要注意的是,攻击者的数量受到训练之前已知的数量的限制。本文介绍了西蒙:一种新的聚合方法,应用基于信誉的迭代过滤技术,即使在存在可能表现出任意行为的攻击者的情况下也能实现鲁棒性。我们比较Simeon国家的最先进的聚合技术,并发现Simeon实现了相当或优越的鲁棒性,各种攻击。值得注意的是,我们表明,Simeon是容忍sybil攻击,其他算法没有,提出了我们的方法的一个关键优势。

英文摘要:

Federated learning enables a global machine learning model to be trained collaboratively by distributed, mutually non-trusting learning agents who desire to maintain the privacy of their training data and their hardware. A global model is distributed to clients, who perform training, and submit their newly-trained model to be aggregated into a superior model. However, federated learning systems are vulnerable to interference from malicious learning agents who may desire to prevent training or induce targeted misclassification in the resulting global model. A class of Byzantine-tolerant aggregation algorithms has emerged, offering varying degrees of robustness against these attacks, often with the caveat that the number of attackers is bounded by some quantity known prior to training. This paper presents Simeon: a novel approach to aggregation that applies a reputation-based iterative filtering technique to achieve robustness even in the presence of attackers who can exhibit arbitrary behaviour. We compare Simeon to state-of-the-art aggregation techniques and find that Simeon achieves comparable or superior robustness to a variety of attacks. Notably, we show that Simeon is tolerant to sybil attacks, where other algorithms are not, presenting a key advantage of our approach.

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。

↑