Machine Learning with Confidential Computing: A Systematization of Knowledge

Abstract

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 paper, 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.

AI Governance Multi-stakeholder Convening

“…Motivation: The integration of hardware mechanisms such as TEEs into AI computing clusters could ensure the confidentiality and integrity of workloads Geppert et al, 2022;Mo et al, 2024) while also greatly aiding with AI security and attestation (Nevo et al, 2024;Kulp et al, 2024;. This in turn would assist in implementing many of the aforementioned problem areas relating to verification and access.…”