Blockchain: Empowering Secure Data Sharing by Meng Shen & Liehuang Zhu & Ke Xu

Author:Meng Shen & Liehuang Zhu & Ke Xu
Language: eng
Format: epub
ISBN: 9789811559396
Publisher: Springer Singapore

5. Secure Heterogeneous Data Sharing Using Blockchain

Meng Shen1 , Liehuang Zhu1 and Ke Xu2

(1)School of Computer Science, Beijing Institute of Technology, Beijing, China

(2)Department of Computer Science, Tsinghua University, Beijing, China

Big data play an extremely important role in different industries. Limited by the data sources between different departments or organizations, data collected by them differ greatly in attributes. These heterogeneous datasets form a complementary relationship with each other, so data sharing between organizations is necessary. Machine learning (ML) methods are widely used in big data processing, thus it is necessary to train machine learning models based on heterogeneous data. In the process of collaborative training machine learning based on heterogeneous data, the current scheme has many challenges, including efficiency, security, and availability in real situations. In this chapter, we propose a secure SVM training mechanism based on the consortium blockchain and threshold homomorphic encryption algorithm. By introducing the consortium blockchain, a decentralized data sharing platform can be constructed, and a secure SVM classifier algorithm can be built based on threshold homomorphic encryption. In order to ensure the efficiency of the model training process, most of the training work is performed locally based on plain text and only necessary shared data need to be encrypted.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.