Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography

TL;DR

This paper proposes using trusted machine learning models as a new approach to enable private inference in complex applications where traditional cryptographic methods are limited, balancing privacy and efficiency.

Contribution

It introduces Trusted Capable Model Environments (TCMEs) as an alternative to cryptography for secure computation, expanding the scope of private inference.

Findings

TCMEs enable private inference for complex problems

Simple cryptographic problems can be solved with TCME

Balances privacy and computational efficiency

Abstract

We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private data. Traditionally, addressing this challenge has involved either seeking trusted intermediaries or constructing cryptographic protocols that restrict how much data is revealed, such as multi-party computations or zero-knowledge proofs. While significant advances have been made in scaling cryptographic approaches, they remain limited in terms of the size and complexity of applications they can be used for. In this paper, we argue that capable machine learning models can fulfill the role of a trusted third party, thus enabling secure computations for applications that were previously infeasible. In particular, we describe Trusted Capable Model Environments (TCMEs) as an alternative approach for scaling secure computation, where capable machine learning model(s) interact under input/output constraints, with explicit information flow control and explicit statelessness. This approach aims to achieve a balance between privacy and computational efficiency, enabling private inference where classical cryptographic solutions are currently infeasible. We describe a number of use cases that are enabled by TCME, and show that even some simple classic cryptographic problems can already be solved with TCME. Finally, we outline current limitations and discuss the path forward in implementing them.