一句话：刻画并优化基于 HE、SS、GC、OT 的端到端私有推理系统，以缓解其过慢难用的问题。
本文研究两端机器学习预测服务中的私有推理（Private Inference, PI）系统：客户端希望查询远程服务器上的已训练模型完成神经网络推理，同时客户端数据和服务器模型都需保密。现有最先进的 PI 协议由离线预处理阶段和在线阶段组成，并组合同态加密（HE）、秘密共享（SS）、乱码电路（GC）和茫然传输（OT）等多种密码原语。尽管需求明确且近期性能已有改进，PI 仍然过于晦涩且速度太慢，难以实际部署。论文对端到端 PI 系统进行刻画与优化，旨在理解其系统瓶颈并提升整体性能，从而推动私有推理的实用化。
In two-party machine learning prediction services, the client’s goal is to query a remote server’s trained machine learning model to perform neural network inference in some application domain. However, sensitive information can be obtained during this process by either the client or the server, leading to potential collection, unauthorized secondary use, and inappropriate access to personal information. These security concerns have given rise to Private Inference (PI), in which both the client’s personal data and the server’s trained model are kept confidential. State-of-the-art PI protocols consist of a pre-processing or offline phase and an online phase that combine several cryptographic primitives: Homomorphic Encryption (HE), Secret Sharing (SS), Garbled Circuits (GC), and Oblivious Transfer (OT). Despite the need and recent performance improvements, PI remains largely arcane today and is too slow for practical use.
@inproceedings{paperbot10060,
title = {Characterizing and Optimizing End-to-End Systems for Private Inference},
author = {Karthik Garimella and Zahra Ghodsi and Nandan Kumar Jha and Siddharth Garg and Brandon Reagen},
booktitle = {ASPLOS},
year = {2023},
doi = {10.1145/3582016.3582065}
}