RevFRF: Enabling Cross-Domain Random Forest Training With Revocable Federated Learning

RevFRF: Enabling Cross-Domain Random Forest Training With Revocable Federated Learning
复制标题

RevFRF:通过可撤销的联邦学习实现跨域随机森林训练

DOI:
10.1109/tdsc.2021.3104842
复制
发表时间:
2021-08
影响因子:
7.3
通讯作者:
Kui Ren
Kui Ren
中科院分区:
计算机科学2区
文献类型:
--
作者:
Yang Liu;Zhuo Ma;Yilong Yang;Ximeng Liu;Jianfeng Ma;Kui Ren

文献摘要

参考文献

相似文献

随机森林是广泛的工业场景中最热门的机器学习工具之一。最近,联合学习实现了高效的分布式机器学习,而不会直接泄露参与者的私有数据。提出了一种新的联邦随机森林(RevFRF)框架,并在此基础上重点讨论了基于RevFRF的联邦学习参与者撤销问题。具体来说,RevFRF首先引入了一套基于同态加密的安全协议来实现联合随机森林(RF)。该协议覆盖了RF模型的整个生命周期,包括构建、预测和参与者撤销。然后,结合RevFRF的实际应用场景,现有的联邦学习框架忽略了一个事实,即即使是联邦学习的每个参与者也不可能永远保持与其他参与者的合作。在公司层面的合作中,允许其余公司使用包含来自离岸公司的记忆的训练有素的模型,可能会导致重大的利益冲突。因此,我们提出了可撤销联邦学习的概念,并说明了RevFRF如何在应用中实现参与者撤销。通过理论分析和实验证明,该协议能够有效地实现联邦射频,并保证被撤销的参与者在训练后的射频中的记忆被安全地移除。
Random forest is one of the most heated machine learning tools in a wide range of industrial scenarios. Recently, federated learning enables efficient distributed machine learning without direct revealing of private participant data. In this article, we present a novel framework of federated random forest (RevFRF), and further emphatically discuss the participant revocation problem of federated learning based on RevFRF. Specifically, RevFRF first introduces a suite of homomorphic encryption based secure protocols to implement federated random forest (RF). The protocols cover the whole lifecycle of an RF model, including construction, prediction and participant revocation. Then, referring to the practical application scenarios of RevFRF, the existing federated learning frameworks ignore a fact that even every participant in federated learning cannot maintain the cooperation with others forever. In company-level cooperation, allowing the remaining companies to use a trained model that contains the memories from an off-lying company potentially leads to a significant conflict of interest. Therefore, we propose the revocable federated learning concept and illustrate how RevFRF implements participant revocation in applications. Through theoretical analysis and experiments, we show that the protocols can efficiently implement federated RF and ensure the memories of a revoked participant in the trained RF to be securely removed.
DOI: 10.1109/icdm.2015.76
发表时间: 2015-11
期刊: 2015 IEEE International Conference on Data Mining
影响因子: --
作者:
Santu Rana;S. Gupta;S. Venkatesh
通讯作者: Santu Rana;S. Gupta;S. Venkatesh
DOI: --
发表时间: 2013-10
期刊: ArXiv
影响因子: --
作者:
Misha Denil;David Matheson;Nando de Freitas
通讯作者: Misha Denil;David Matheson;Nando de Freitas
DOI: 10.1007/978-3-642-03129-8_7
发表时间: 2010-01-01
期刊: TOWARDS A THEORY OF THINKING: BUILDING BLOCKS FOR A CONCEPTUAL FRAMEWORK
影响因子: --
作者:
Goldstone, Robert L.;Day, Sam;Son, Ji Y.
通讯作者: Son, Ji Y.
具有多个密钥的高效保护隐私的外包计算工具包
DOI: 10.1109/tifs.2016.2573770
发表时间: 2016-11-01
影响因子: 6.8
作者:
Liu, Ximeng;Deng, Robert H.;Weng, Jian
通讯作者: Weng, Jian
DOI: 10.48550/arxiv.2301.02621
发表时间: 2022-12
期刊: ArXiv
影响因子: --
作者:
Yaqiong Mu
通讯作者: Yaqiong Mu