Confidential machine learning on untrusted platforms:a survey
作者机构:Northwestern Mutual Data Science Associate Professor Director of Trustworthy and Intelligent Computing Lab Department of Computer Science Marquette University MilwaukeeWisconsinUSA HP Inc.USA
出 版 物:《Cybersecurity》 (网络空间安全科学与技术(英文))
年 卷 期:2021年第4卷第1期
页 面:461-479页
核心收录:
学科分类:0810[工学-信息与通信工程] 1205[管理学-图书情报与档案管理] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0839[工学-网络空间安全] 08[工学] 081104[工学-模式识别与智能系统] 0835[工学-软件工程] 0811[工学-控制科学与工程] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:the National Science Foundation under grant no.1245847 the National Institute of Health under grant no.1R43AI136357-01A1
主 题:Confidential computing Cryptographic protocols Machine learning
摘 要:With the ever-growing data and the need for developing powerful machine learning models,data owners increasingly depend on various untrusted platforms(e.g.,public clouds,edges,and machine learning service providers)for scalable processing or collaborative ***,sensitive data and models are in danger of unauthorized access,misuse,and privacy compromises.A relatively new body of research confidentially trains machine learning models on protected data to address these *** this survey,we summarize notable studies in this emerging area of *** a unified framework,we highlight the critical challenges and innovations in outsourcing machine learning *** focus on the cryptographic approaches for confidential machine learning(CML),primarily on model training,while also covering other directions such as perturbation-based approaches and CML in the hardware-assisted computing *** discussion will take a holistic way to consider a rich context of the related threat models,security assumptions,design principles,and associated trade-offs amongst data utility,cost,and confidentiality.