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
  • [1] Confidential machine learning on untrusted platforms: a survey
    Sagar, Sharma
    Keke, Chen
    CYBERSECURITY, 2021, 4 (01)
  • [2] Confidential machine learning on untrusted platforms: a survey
    Sharma Sagar
    Chen Keke
    Cybersecurity, 4
  • [3] A Machine Learning Security Framework for Iot Systems
    Bagaa, Miloud
    Taleb, Tarik
    Bernabe, Jorge Bernal
    Skarmeta, Antonio
    IEEE ACCESS, 2020, 8 : 114066 - 114077
  • [4] Evolutionary Computation and Machine Learning in Security
    Picek, Stjepan
    Jakobovic, Domagoj
    PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022, 2022, : 1572 - 1601
  • [5] Computation Offloading for Machine Learning in Industrial Environments
    Guo, Mian
    Mukherjee, Mithun
    Liang, Gen
    Zhang, Jinyou
    IECON 2020: THE 46TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2020, : 4465 - 4470
  • [6] Security Perspective of Biometric Recognition and Machine Learning Techniques
    Arslan, Bilgehan
    Yorulmaz, Ezgi
    Akca, Burcin
    Sagiroglu, Seref
    2016 15TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2016), 2016, : 492 - 497
  • [7] Two Sides of the Same Coin: Boons and Banes of Machine Learning in Hardware Security
    Liu, Wenye
    Chang, Chip-Hong
    Wang, Xueyang
    Liu, Chen
    Fung, Jason M.
    Ebrahimabadi, Mohammad
    Karimi, Naghmeh
    Meng, Xingyu
    Basu, Kanad
    IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS, 2021, 11 (02) : 228 - 251
  • [8] Robust Machine Learning Systems: Reliability and Security for Deep Neural Networks
    Hanif, Muhammad Abdullah
    Khalid, Faiq
    Putra, Rachmad Vidya Wicaksana
    Rehman, Semeen
    Shafique, Muhammad
    2018 IEEE 24TH INTERNATIONAL SYMPOSIUM ON ON-LINE TESTING AND ROBUST SYSTEM DESIGN (IOLTS 2018), 2018, : 257 - 260
  • [9] Machine Learning for Optical Network Security Monitoring: A Practical Perspective
    Furdek, Marija
    Natalino, Carlos
    Lipp, Fabian
    Hock, David
    Di Giglio, Andrea
    Schiano, Marco
    JOURNAL OF LIGHTWAVE TECHNOLOGY, 2020, 38 (11) : 2860 - 2871
  • [10] Security of Machine Learning-Based Anomaly Detection in Cyber Physical Systems
    Jadidi, Zahra
    Pal, Shantanu
    Nayak, Nithesh K.
    Selvakkumar, Arawinkumaar
    Chang, Chih-Chia
    Beheshti, Maedeh
    Jolfaei, Alireza
    2022 31ST INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATIONS AND NETWORKS (ICCCN 2022), 2022,