信任的機器學習模型為目前無法使用密碼學解決的問題開啟私密推論。

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

我們經常與不受信任的對象互動。隱私優先原則可能限制這些互動的效果，因為實現某些目標需要共享私人數據。傳統上，應對這一挑戰通常涉及尋求可信中介或構建加密協議，限制數據揭露的範圍，例如多方計算或零知識證明。儘管加密方法取得了重大進展，但在可應用的應用程序規模和複雜性方面仍存在限制。本文主張，具有能力的機器學習模型可以擔任可信第三方的角色，從而實現以前難以實現的應用程序的安全計算。具體而言，我們描述了可信能力模型環境（TCME）作為擴展安全計算的替代方法，其中具有能力的機器學習模型在輸入/輸出約束下進行交互，具有明確的信息流控制和明確的無狀態性。這種方法旨在在隱私和計算效率之間取得平衡，實現私密推論，而傳統的加密解決方案目前難以實現。我們描述了TCME所啟用的一些用例，並展示即使是一些簡單的經典加密問題也可以使用TCME解決。最後，我們概述了目前的限制並討論實施的未來方向。

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.