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
  • [41] Securing IoT-Empowered Fog Computing Systems: Machine Learning Perspective
    Ahanger, Tariq Ahamed
    Tariq, Usman
    Ibrahim, Atef
    Ullah, Imdad
    Bouteraa, Yassine
    Gebali, Fayez
    MATHEMATICS, 2022, 10 (08)
  • [42] Detection of Android Malware Using Machine Learning and Siamese Shot Learning Technique for Security
    Almarshad, Fahdah A.
    Zakariah, Mohammed
    Gashgari, Ghada Abdalaziz
    Aldakheel, Eman Abdullah
    Alzahrani, Abdullah I. A.
    IEEE ACCESS, 2023, 11 : 127697 - 127714
  • [43] Security and Privacy in E-Health Systems: A Review of AI and Machine Learning Techniques
    Nankya, Mary
    Mugisa, Allan
    Usman, Yusuf
    Upadhyay, Aadesh
    Chataut, Robin
    IEEE ACCESS, 2024, 12 : 148796 - 148816
  • [44] Static Analysis of Information Systems for IoT Cyber Security: A Survey of Machine Learning Approaches
    Kotenko, Igor
    Izrailov, Konstantin
    Buinevich, Mikhail
    SENSORS, 2022, 22 (04)
  • [45] The security of machine learning
    Marco Barreno
    Blaine Nelson
    Anthony D. Joseph
    J. D. Tygar
    Machine Learning, 2010, 81 : 121 - 148
  • [46] Learnable Audio Encryption for Untrusted Outsourcing Machine Learning Services
    Chi, Po-Wen
    Hsiao, Pin-Hsin
    2019 14TH ASIA JOINT CONFERENCE ON INFORMATION SECURITY (ASIAJCIS 2019), 2019, : 151 - 156
  • [47] The security of machine learning
    Barreno, Marco
    Nelson, Blaine
    Joseph, Anthony D.
    Tygar, J. D.
    MACHINE LEARNING, 2010, 81 (02) : 121 - 148
  • [48] Security for Machine Learning-based Software Systems: A Survey of Threats, Practices, and Challenges
    Chen, Huaming
    Babar, M. Ali
    ACM COMPUTING SURVEYS, 2024, 56 (06)
  • [49] The rise of scientific machine learning: a perspective on combining mechanistic modelling with machine learning for systems biology
    Noordijk, Ben
    Gomez, Monica L. Garcia
    ten Tusscher, Kirsten H. W. J.
    de Ridder, Dick
    van Dijk, Aalt D. J.
    Smith, Robert W.
    FRONTIERS IN SYSTEMS BIOLOGY, 2024, 4
  • [50] Towards Security Threats of Deep Learning Systems: A Survey
    He, Yingzhe
    Meng, Guozhu
    Chen, Kai
    Hu, Xingbo
    He, Jinwen
    IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2022, 48 (05) : 1743 - 1770