Privacy-Preserving Deep Learning Based on Multiparty Secure Computation: A Survey

Deep learning (DL) has demonstrated superior success in various of applications, such as image classification, speech recognition, and anomalous detection. The unprecedented performance gain of DL largely depends on tremendous training data, high-performance computation resources, and well-designed...

Full description

Saved in:
Bibliographic Details
Published in:IEEE internet of things journal Vol. 8; no. 13; pp. 10412 - 10429
Main Authors: Zhang, Qiao, Xin, Chunsheng, Wu, Hongyi
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.07.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Cloud computing
Computational modeling
Data encryption
Data models
Data privacy
Deep learning
Deep learning (DL)
Image classification
linear and nonlinear computations
Machine learning
Mathematical models
Object recognition
Outsourcing
Parameters
Predictive models
Privacy
privacy preserving
Servers
Speech recognition
State-of-the-art reviews
Training
ISSN:2327-4662, 2327-4662
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning (DL) has demonstrated superior success in various of applications, such as image classification, speech recognition, and anomalous detection. The unprecedented performance gain of DL largely depends on tremendous training data, high-performance computation resources, and well-designed model structures. However, privacy concerns raise from such necessities. First, as the training data are usually distributed among multiple parties, directly exposing and collecting such large amount of data could violate the laws especially for private information, such as personal identities, medical records, and financial profiles. Second, locally deploying advantageous computation resources is costly for individual party having partial data. Third, direct release of well-trained model parameters threatens the information about training data or the intellectual property of model owners. Therefore, individual party prefers outsourcing computation (data) in a secure way to powerful cloud servers such as Microsoft Azure, and how to enable the cloud servers to perform DL algorithms without revealing data owners' private information and model owners' valuable parameters is emerging as an urgent task, which is termed as privacy-preserving (outsourcing) DL. In this article, we review the state-of-the-art researches in privacy-preserving DL based on multiparty secure computation with data encryption and summarize these techniques in both training phase and inference phase. Specifically, we categorize the techniques with respect to the linear and nonlinear computations, which are the two basic building blocks in DL. Following a comprehensive overview of each research scheme, we present primary technical hurdles needed to be addressed and discuss several promising directions for future research.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2327-4662
2327-4662
DOI:10.1109/JIOT.2021.3058638