数据与计算发展前沿2024，Vol.6Issue(5)：1-12,12.DOI:10.11871/jfdc.issn.2096-742X.2024.05.001
机器学习安全推理研究综述
Review of Research on Secure Inference in Machine Learning
摘要
Abstract
[Objective]This paper analyzes existing research on secure machine learning inference and proposes future research directions.[Methods]Using the security assumptions of different schemes as a basis for classification,this study conducts analysis and comparison of secure inference techniques that utilize various technological combinations for application in differ-ent machine learning contexts.[Results]While current schemes facilitate secure machine learning inference,they exhibit limitations in computational efficiency,security,scalability,and practical applicability.[Limitations]Due to limited data availability,experiments and comparisons of the analyzed schemes under the same benchmark were not conducted.[Con-clusions]Designing secure machine learning inference schemes based on application scenari-os,ensuring security while improving usability and reducing costs,will be a sustained devel-opment direction in this field.关键词
隐私保护机器学习/机器学习/数据隐私/安全多方计算Key words
privacy-preserving machine learning/machine learning/data privacy/secure multi-party computation引用本文复制引用
龙春,李丽莎,李婧,杨帆,魏金侠,付豫豪..机器学习安全推理研究综述[J].数据与计算发展前沿,2024,6(5):1-12,12.基金项目
国家重点研发计划(2023YFC3304704) （2023YFC3304704）
中国科学院网络安全和信息化专项(CAS-WX2022GC-04) （CAS-WX2022GC-04）
中国科学院青年创新促进会项目(2022170) （2022170）
