密码学报（中英文）2024，Vol.11Issue(4)：771-798,28.DOI:10.13868/j.cnki.jcr.000705
隐私保护深度学习研究综述
A Survey on Privacy-Preserving Deep Learning
摘要
Abstract
In deep learning as a service(DLaaS),private data constantly flow among various parties,which inevitably leads to privacy risks.On one hand,data owners worry about the possible exposure of their private data to service providers when they directly upload the data in plaintext.On the other hand,model owners are concerned about that adversaries may steal their costly trained models during extensive data interactions.As a result,combining privacy protection with deep learning has become a hot research topic these days.This paper reviews the research results in privacy-preserving deep learning since 2016,and categorizes the techniques into linear and nonlinear computations,which are the two basic building blocks in deep learning models.Specifically,the pros and cons of diverse tech-niques used in different layers are presented according to time and quantity statistics.In addition,the evolutionary directions of every technique are clarified by tracing their optimization routes.Following a comprehensive overview of each representative research scheme,the hurdles of privacy-preserving deep learning are listed and the resolution as well as promising directions for further research are proposed.关键词
隐私保护深度学习/同态加密/秘密共享/不经意传输/混淆电路Key words
privacy-preserving deep learning/homomorphic encryption/secret sharing/oblivious transfer/garbled circuit分类
信息技术与安全科学引用本文复制引用
陈品极,何琨,陈晶,杜瑞颖..隐私保护深度学习研究综述[J].密码学报（中英文）,2024,11(4):771-798,28.基金项目
国家重点研发计划(2022YFB3102100) （2022YFB3102100）
国家自然科学基金(62076187,62172303) （62076187,62172303）
湖北省重点研发计划(2022BAA039) （2022BAA039）
山东省重点研发计划(2022CXPT055)National Key Research and Development Program of China(2022YFB3102100) （2022CXPT055）
National Natural Science Foundation of China(62076187,62172303) （62076187,62172303）
Key Research and Development Program of Hubei Province(2022BAA039) （2022BAA039）
Key Research and Development Program of Shandong Province(2022CXPT055) （2022CXPT055）
