E-Booster: An FPGA-based Accelerator for Secure Tree Boosting Using Additively Homomorphic Encryption

Tree boosting is a widely used machine learning model in many financial fields. Additively homomorphic encryption is an important cryptographic tool used for secure tree boosting in the setting of federated learning. However, homomorphic encryption includes computationally expensive operations. Curr...

Full description

Saved in:
Bibliographic Details
Published in:IEEE MICRO 2023-07, p.1-8
Main Authors: Wu, Guiming, He, Qianwen, Jiang, Jiali, Zhang, Zhenxiang, Shi, Yunfeng, Long, Xin, Jiang, Linquan, Li, Shuangchen, Xie, Yuan, Wei, Changzheng, Zhao, Yuan, Yan, Ying, Zhang, Hui, Zou, Yinchao
Format: Article
Language:English
Subjects:
Boosting
Computational modeling
Cryptography
Federated learning
Histograms
Homomorphic encryption
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Tree boosting is a widely used machine learning model in many financial fields. Additively homomorphic encryption is an important cryptographic tool used for secure tree boosting in the setting of federated learning. However, homomorphic encryption includes computationally expensive operations. Current frameworks for secure tree boosting are extremely slow. In this article, we propose E-Booster, a novel accelerator for the training of secure tree boosting. E-Booster can fully exploit algorithmic superiority and architectural optimization to achieve unprecedented performance and to address the obstacle in deploying additively homomorphic encryption in industrial applications. E-Booster has been implemented on an Intel Agilex FPGA and evaluated on four public datasets. It achieves 5.1-7.8× speedup over a CPU with 32 threads for secure tree boosting. To the best of our knowledge, E-Booster is the first additively homomorphic encryption accelerator that can be applied to industrial secure tree boosting.
ISSN:0272-1732
DOI:10.1109/MM.2023.3293845