可信的机器学习模型为目前使用加密技术难以实现的问题解锁私密推断。

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

January 15, 2025

作者: Ilia Shumailov, Daniel Ramage, Sarah Meiklejohn, Peter Kairouz, Florian Hartmann, Borja Balle, Eugene Bagdasarian

cs.AI

摘要

我们经常与不受信任的方进行互动。隐私优先级可能会限制这些互动的有效性，因为实现某些目标需要共享私人数据。传统上，解决这一挑战通常涉及寻求可信中介或构建密码协议来限制数据的泄露量，比如多方计算或零知识证明。尽管在扩展密码方法方面取得了重大进展，但它们在可用于的应用程序的规模和复杂性方面仍然存在限制。在本文中，我们认为，能力强大的机器学习模型可以充当可信第三方的角色，从而实现先前无法实现的应用程序的安全计算。具体来说，我们描述了可信能力模型环境（TCME）作为扩展安全计算的替代方法，其中能力强大的机器学习模型在输入/输出约束下进行交互，具有明确的信息流控制和明确的无状态性。这种方法旨在在隐私和计算效率之间取得平衡，实现私人推断，而传统的密码解决方案目前无法实现。我们描述了几个由TCME实现的用例，并展示了即使一些简单的经典密码问题也可以通过TCME解决。最后，我们概述了当前的限制，并讨论了实施它们的未来路径。

English

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.