You are looking at a specific version 20220105:193656 of this paper. See the latest version.

Paper 2021/1603

CHEX-MIX: Combining Homomorphic Encryption with Trusted Execution Environments for Two-party Oblivious Inference in the Cloud

Deepika Natarajan and Wei Dai and Ronald Dreslinski

Abstract

Data, when coupled with state-of-the-art machine learning models, can enable remarkable applications. But, there exists an underlying tension: users wish to keep their data private, and model providers wish to protect their intellectual property. Homomorphic encryption (HE) and multi-party computation (MPC) techniques have been proposed as solutions to this problem; however, both techniques require model providers to fully trust the server performing the machine learning computation. This limits the scale of inference applications since it prevents model providers from leveraging shared public cloud infrastructures. In this work, we present CHEX-MIX, a solution to the problem of privacy-preserving machine learning between two mutually distrustful parties in an untrusted cloud setting. CHEX-MIX relies on a combination of HE and trusted execution environments (TEEs) and leverages the benefits of each to counter the drawbacks of the other. In particular, we use HE to provide clients with confidentiality guarantees and TEEs to provide model providers with confidentiality guarantees and protect the integrity of computation from malicious cloud adversaries. Unlike prior solutions to this problem, such as multi-key HE, single-key HE, MPC, or TEE-only techniques, our solution assumes that both clients and the cloud can be malicious, makes no collusion assumptions, and frees model providers from needing to maintain private online infrastructures. In this paper, we analyze our solution from a security perspective and detail the advantages that our solution provides over prior works, including its ability to allow model providers to maintain privacy of their software IP. We demonstrate the feasibility of our solution by deploying CHEX-MIX in an Azure confidential computing machine. Our results show that CHEX-MIX can execute at high efficiency, with low communication cost, while providing security guarantees unaddressed by prior work.

Metadata
Available format(s)
PDF
Category
Cryptographic protocols
Publication info
Preprint. MINOR revision.
Keywords
oblivious inferencehomomorphic encryptiontrusted execution environmentprivacy-preserving machine learning
Contact author(s)
dnataraj @ umich edu
wei dai @ microsoft com
History
2023-07-03: last of 3 revisions
2021-12-09: received
See all versions
Short URL
https://ia.cr/2021/1603
License
Creative Commons Attribution
CC BY
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.