可信机器学习模型为当前密码学无法解决的问题解锁私有推理能力
Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography
AI总结：
针对传统密码学方案在大规模复杂应用中私有推理受限的问题，提出可信能力模型环境（TCMEs），以强能力机器学习模型作为可信第三方，在输入输出约束、显式信息流控制与无状态特性下实现隐私与效率的平衡，为密码学无法覆盖的场景提供私有推理支持。
摘要：
我们经常与不可信的参与方交互。对隐私的优先考量可能会限制这类交互的有效性，因为实现特定目标需要共享私有数据。传统上，应对这一挑战的方式要么是寻找可信中介，要么是构建限制数据泄露量的密码学协议，例如安全多方计算或零知识证明。尽管密码学方法在可扩展性方面已取得重大进展，但它们在可应用的程序规模和复杂度上仍存在局限。本文中，我们提出能力强大的机器学习模型可以承担可信第三方的角色，从而为以往无法实现的应用场景提供安全计算支持。具体而言，我们将可信能力模型环境（Trusted Capable Model Environments，TCMEs）描述为一种扩展安全计算的替代方案，其中具备强能力的机器学习模型在输入/输出约束下交互，且具备显式信息流控制和显式无状态特性。该方法旨在实现隐私与计算效率之间的平衡，为经典密码学方案目前无法解决的场景提供私有推理支持。我们列举了TCME可支持的多个用例，并表明即使是一些简单的经典密码学问题也已能通过TCME解决。最后，我们概述了当前的局限性，并讨论了其落地实施的未来路径。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
