Blockchain-based Secure Aggregation for Federated Learning with a Traffic Prediction Use Case

【Author】 Zhang, Qiong; Palacharla, Paparao; Sekiya, Motoyoshi; Suga, Junichi; Katagiri, Toru

【Source】PROCEEDINGS OF THE 2021 IEEE 7TH INTERNATIONAL CONFERENCE ON NETWORK SOFTWARIZATION (NETSOFT 2021): ACCELERATING NETWORK SOFTWARIZATION IN THE COGNITIVE AGE

【Abstract】Federated learning is a distributed machine learning approach that can be applied to many networking applications. In this paper, we propose a novel blockchain-based secure aggregation protocol for federated learning, which simplifies the existing secure aggregation process by leveraging consensus through blockchain. We demonstrate the prototype by training a general LSTM model for traffic prediction at cell sites based on distributed time series datasets.

【Keywords】

【标题】基于区块链的联邦学习安全聚合与流量预测用例

【摘要】联邦学习是一种分布式机器学习方法，可以应用于许多网络应用程序。在本文中，我们提出了一种新颖的基于区块链的联邦学习安全聚合协议，该协议通过利用区块链的共识来简化现有的安全聚合过程。我们通过训练基于分布式时间序列数据集的蜂窝站点流量预测的通用 LSTM 模型来演示原型。

【关键词】无

【发表时间】2021

【收录时间】2022-07-06

【文献类型】Proceedings Paper

【论文大主题】区块链联邦学习

【论文小主题】联邦学习为主体

【翻译者】石东瑛