RePEL: Blockchain-Empowered Conditional Privacy-Preserving Encrypted Learning

Business organization performs its business activities within a headquarter-branch relationship, especially for multinationals, by establishing work places in accordance with business requirements. The data-driven decision making stimulates the importance of data analysis. Machine learning, as a met...

Full description

Saved in:
Bibliographic Details
Published in:IEEE internet of things journal 2022-07, Vol.9 (14), p.1-1
Main Authors: Jiang, Peng, Yang, Chenjie, Zhu, Liehuang
Format: Article
Language:English
Subjects:
Algorithms
Blockchain
Blockchains
Business
Conditional Privacy
Cryptography
Data analysis
Data privacy
Data transfer (computers)
Decision analysis
Decision making
Encryption
Functional Encryption
Iron
Machine learning
Machine Learning over Encrypted Data
Performance evaluation
Privacy
Reliability
Reliability aspects
Security
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Business organization performs its business activities within a headquarter-branch relationship, especially for multinationals, by establishing work places in accordance with business requirements. The data-driven decision making stimulates the importance of data analysis. Machine learning, as a method of data analysis, automates analytical model building based on the idea that systems can train and learn from data to make decisions with minimal human intervention. For high accuracy, traditional machine learning algorithms make design trade-offs, conceding privacy and reliability and are thereby unable to satisfy strong security demands. To resolve design tensions, in this paper, we propose RePEL, which harmonizes functional encryption and blockchain on top of encrypted learning. RePEL allows headquarter to only share partial information about business data collected from branches while manages data transfer with consensus mechanism in blockchain, which works in a coordinated way for preserving conditional privacy and high reliability. We instantiate a RePEL design with the three-layer framework and formally reduce its security to a provably-secure functional encryption scheme. We further deploy Feel_BC to implement a RePEL prototype system, so as to realize the performance evaluation. Experimental results show that RePEL, with the basic premise of privacy and reliability, can achieve high accuracy and reasonable throughputs.
ISSN:2327-4662
2327-4662
DOI:10.1109/JIOT.2021.3138076