Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspective

被引:4
|
作者
Duy, Kha Dinh [1 ]
Noh, Taehyun [1 ]
Huh, Siwon [1 ]
Lee, Hojoon [1 ]
机构
[1] Sungkyunkwan Univ, Dept Comp Sci & Engn, Nat Sci Campus, Suwon 16419, Gyeonggi Do, South Korea
基金
新加坡国家研究基金会;
关键词
Security; Computational modeling; Hardware; Data models; Software; Machine learning; Codes; Confidential machine learning computation; trusted execution; side-channel attacks; multi-party ML computation; ATTACKS;
D O I
10.1109/ACCESS.2021.3136889
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
As machine learning (ML) technologies and applications are rapidly changing many computing domains, security issues associated with ML are also emerging. In the domain of systems security, many endeavors have been made to ensure ML model and data confidentiality. ML computations are often inevitably performed in untrusted environments and entail complex multi-party security requirements. Hence, researchers have leveraged the Trusted Execution Environments (TEEs) to build confidential ML computation systems. We conduct a systematic and comprehensive survey by classifying attack vectors and mitigation in confidential ML computation in untrusted environments, analyzing the complex security requirements in multi-party scenarios, and summarizing engineering challenges in confidential ML implementation. Lastly, we suggest future research directions based on our study.
引用
收藏
页码:168656 / 168677
页数:22
相关论文
共 50 条
  • [31] Machine Learning in IoT Security: Current Solutions and Future Challenges
    Hussain, Fatima
    Hussain, Rasheed
    Hassan, Syed Ali
    Hossain, Ekram
    IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2020, 22 (03): : 1686 - 1721
  • [32] Literature Review of Machine Learning and Threat Intelligence in Cloud Security
    Thaqi, Rrezearta
    Krasniqi, Bujar
    Mazrekaj, Artan
    Rexha, Blerim
    IEEE ACCESS, 2025, 13 : 11663 - 11678
  • [33] Architecting Effectual Computation for Machine Learning Accelerators
    Lu, Hang
    Zhang, Mingzhe
    Han, Yinhe
    Wang, Qi
    Li, Huawei
    Li, Xiaowei
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2020, 39 (10) : 2654 - 2667
  • [34] Machine Learning Security Against Data Poisoning: Are We There Yet?
    Cina, Antonio Emanuele
    Grosse, Kathrin
    Demontis, Ambra
    Biggio, Battista
    Roli, Fabio
    Pelillo, Marcello
    COMPUTER, 2024, 57 (03) : 26 - 34
  • [35] Challenges of modeling and analysis in cybermanufacturing: a review from a machine learning and computation perspective
    SungKu Kang
    Ran Jin
    Xinwei Deng
    Ron S. Kenett
    Journal of Intelligent Manufacturing, 2023, 34 : 415 - 428
  • [36] Multiagent Systems: A Survey from a Machine Learning Perspective
    Peter Stone
    Manuela Veloso
    Autonomous Robots, 2000, 8 : 345 - 383
  • [37] Challenges of modeling and analysis in cybermanufacturing: a review from a machine learning and computation perspective
    Kang, SungKu
    Jin, Ran
    Deng, Xinwei
    Kenett, Ron S.
    JOURNAL OF INTELLIGENT MANUFACTURING, 2023, 34 (02) : 415 - 428
  • [38] Multiagent systems: A survey from a machine learning perspective
    Stone, P
    Veloso, M
    AUTONOMOUS ROBOTS, 2000, 8 (03) : 345 - 383
  • [39] Online Social Network Security: A Comparative Review Using Machine Learning and Deep Learning
    Chanchal Kumar
    Taran Singh Bharati
    Shiv Prakash
    Neural Processing Letters, 2021, 53 : 843 - 861
  • [40] Online Social Network Security: A Comparative Review Using Machine Learning and Deep Learning
    Kumar, Chanchal
    Bharati, Taran Singh
    Prakash, Shiv
    NEURAL PROCESSING LETTERS, 2021, 53 (01) : 843 - 861