Machine Learning with Confidential Computing: A Systematization of Knowledge
ACM Computing Surveys · 30.11.2024 · 56 (11) · 1-40
DOI: 10.1145/3670007 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 29.06.2024. Verfasst von Fan Mo und 2 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 282 Literaturangaben.
Abstract (Originalsprache)
Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML’s pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential Computing has been utilized in both academia and industry to mitigate privacy and security issues in various ML scenarios. In this article, the conjunction between ML and Confidential Computing is investigated. We systematize the prior work on Confidential Computing-assisted ML techniques that provide (i ) confidentiality guarantees and (ii ) integrity assurances and discuss their advanced features and drawbacks. Key challenges are further identified, and we provide dedicated analyses of the limitations in existing Trusted Execution Environment (TEE) systems for ML use cases. Finally, prospective works are discussed, including grounded privacy definitions for closed-loop protection, partitioned executions of efficient ML, dedicated TEE-assisted designs for ML, TEE-aware ML, and ML full pipeline guarantees. By providing these potential solutions in our systematization of knowledge, we aim to build the bridge to help achieve a much stronger TEE-enabled ML for privacy guarantees without introducing computation and system costs.
Zitieren
APA
Mo, F., Tarkhani, Z., & Haddadi, H. (2024). Machine Learning with Confidential Computing: A Systematization of Knowledge. ACM Computing Surveys, 56(11), 1-40. https://doi.org/10.1145/3670007
Vancouver
Mo F, Tarkhani Z, Haddadi H. Machine Learning with Confidential Computing: A Systematization of Knowledge. ACM Computing Surveys. 2024;56(11):1-40. doi:10.1145/3670007
BibTeX
@article{Mo2024,
author = {Mo, Fan and Tarkhani, Zahra and Haddadi, Hamed},
title = {Machine Learning with Confidential Computing: A Systematization of Knowledge},
journal = {ACM Computing Surveys},
year = {2024},
volume = {56},
number = {11},
pages = {1--40},
doi = {10.1145/3670007}
}
EUVIMED