arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.13643cs.CRcs.LG
收藏

MPC-Pipe:一种用于安全多方机器学习推理的高效流水线方案

MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inference

University of Southern California(南加利福尼亚大学)

Yongqin Wang, Rachit Rajat, Murali Annavaram

AI总结:

本文提出MPC-Pipe,一种用于安全多方机器学习训练和推理的高效系统,通过流水线化在线阶段的计算与通信以实现重叠,有效提升了ML工作负载的吞吐量与延迟性能。

摘要:

在过去几年中,多方计算(MPC)作为一种安全计算模型越来越受欢迎。然而,先前的工作表明,与明文相比,MPC协议仍然面临巨大的性能损失,特别是在应用于ML算法时。这种开销是由额外的计算和通信成本引起的。先前的研究以及我们自己的分析发现,当今大多数MPC协议都是顺序执行通信和计算的。参与方必须首先计算其份额,然后进行数据通信以分发新的秘密份额,然后才能进行下一步计算。在这项工作中,我们表明这种串行化是不必要的,特别是在ML计算(包括卷积神经网络和基于Transformer的模型)的上下文中。我们证明,可以精心协调计算和通信步骤以实现重叠。我们提出了MPC-Pipe,这是一个用于ML工作负载训练和推理的高效MPC系统,它在在线阶段将MPC协议中的计算和通信进行流水线化。MPC-Pipe提出了三种流水线方案,以在半诚实多数对手设置下优化ML的在线阶段。我们通过增强CrypTen的修改版本来实现MPC-Pipe,该版本分离了在线和离线阶段。我们使用深度神经网络(VGG16、ResNet50)和Transformer在不同网络设置下评估了MPC在线阶段的端到端系统性能优势。我们表明,MPC-Pipe能够提升ML工作负载的吞吐量和降低延迟。

英文摘要:

Multi-party computing (MPC) has been gaining popularity as a secure computing model over the past few years. However, prior works have demonstrated that MPC protocols still pay substantial performance penalties compared to plaintext, particularly when applied to ML algorithms. The overhead is due to added computation and communication costs. Prior studies, as well as our own analysis, found that most MPC protocols today sequentially perform communication and computation. The participating parties must compute on their shares first and then perform data communication to allow the distribution of new secret shares before proceeding to the next computation step. In this work, we show that serialization is unnecessary, particularly in the context of ML computations (both in Convolutional neural networks and in Transformer-based models). We demonstrate that it is possible to carefully orchestrate the computation and communication steps to overlap. We propose MPC-Pipe, an efficient MPC system for both training and inference of ML workloads, which pipelines computations and communications in an MPC protocol during the online phase. MPC-Pipe proposes three pipeline schemes to optimize the online phase of ML in the semi-honest majority adversary setting. We implement MPC-Pipe by augmenting a modified version of CrypTen, which separates online and offline phases. We evaluate the end-to-end system performance benefits of the online phase of MPC using deep neural networks (VGG16, ResNet50) and Transformers using different network settings. We show that MPC-Pipe can improve the throughput and latency of ML workloads.

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。

↑