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
  • [21] Secure Multi-Party Computation for Machine Learning: A Survey
    Zhou, Ian
    Tofigh, Farzad
    Piccardi, Massimo
    Abolhasan, Mehran
    Franklin, Daniel
    Lipman, Justin
    IEEE ACCESS, 2024, 12 : 53881 - 53899
  • [22] Blockchain and Machine Learning in EHR Security: A Systematic Review
    Zukaib, Umer
    Cui, Xiaohui
    Hassan, Mir
    Harris, Sheetal
    Hadi, Hassan Jalil
    Zheng, Chengliang
    IEEE ACCESS, 2023, 11 : 130230 - 130256
  • [23] Enhancing IoT Security and Privacy with Trusted Execution Environments and Machine Learning
    Yuhala, Peterson
    2023 53RD ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS - SUPPLEMENTAL VOLUME, DSN-S, 2023, : 176 - 178
  • [24] Machine Learning Techniques for Security of Internet of Things (IoT) and Fog Computing Systems
    Moh, Melody
    Raju, Robinson
    PROCEEDINGS 2018 INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING & SIMULATION (HPCS), 2018, : 709 - 715
  • [25] Security Engineering with Machine Learning for Adversarial Resiliency in Mobile Cyber Physical Systems
    Olowononi, Felix O.
    Rawat, Danda B.
    Garuba, Moses
    Kamhoua, Charles
    ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS, 2019, 11006
  • [26] "I Never Thought About Securing My Machine Learning Systems": A Study of Security and Privacy Awareness of Machine Learning Practitioners
    Boenisch, Franziska
    Battis, Verena
    Buchmann, Nicolas
    Poikela, Maija
    MENSCH AND COMPUTER 2021 (MUC 21), 2021, : 520 - 546
  • [27] Security Transmission Scheme of NOMA Systems With an Untrusted Near User
    Li, Enyu
    Wang, Rongyu
    Yang, Wen
    Dai, Afei
    Zhang, Yue
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2025, 74 (01) : 599 - 610
  • [28] The Dark Side: Security and Reliability Concerns in Machine Learning for EDA
    Xie, Zhiyao
    Pan, Jingyu
    Chang, Chen-Chia
    Hu, Jiang
    Chen, Yiran
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2023, 42 (04) : 1171 - 1184
  • [29] A Survey on Machine Learning in Hardware Security
    Koylu, Troya Cagil
    Reinbrecht, Cezar Rodolfo Wedig
    Gebregiorgis, Anteneh
    Hamdioui, Said
    Taouil, Mottaqiallah
    ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS, 2023, 19 (02)
  • [30] 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