Delphi: A Cryptographic Inference System for Neural Networks
Delphi: A Cryptographic Inference System for Neural Networks
复制标题
DOI：
10.1145/3411501.3419418
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Pratyush Mishra;Ryan T. Lehmkuhl;Akshayaram Srinivasan;Wenting Zheng;Raluca A. Popa
中科院分区：
文献类型：
--
作者：
Pratyush Mishra;Ryan T. Lehmkuhl;Akshayaram Srinivasan;Wenting Zheng;Raluca A. Popa
许多公司为用户提供广泛应用的神经网络预测服务。然而，目前的预测系统损害了一方的隐私：要么用户必须向服务提供商发送敏感输入进行分类，要么服务提供商必须将其专有神经网络存储在用户的设备上。前者损害了用户的个人隐私，而后者暴露了服务提供商的专有模式。我们设计、实现和评估了Delphi，这是一个安全的预测系统，允许双方执行神经网络推理，而不会泄露任何一方的数据。Delphi通过同时联合设计密码学和机器学习来解决这个问题。我们首先设计了一种混合密码协议，该协议在以往工作的基础上改进了通信和计算成本。其次，我们开发了一个规划器，它自动生成神经网络体系结构配置，以在我们的混合协议的性能和精度之间进行权衡。总而言之，这些技术使我们能够实现与最先进的先前工作相比，在线预测延迟提高22倍。
Many companies provide neural network prediction services to users for a wide range of applications. However, current prediction systems compromise one party's privacy: either the user has to send sensitive inputs to the service provider for classification, or the service provider must store its proprietary neural networks on the user's device. The former harms the personal privacy of the user, while the latter reveals the service provider's proprietary model. We design, implement, and evaluate Delphi, a secure prediction system that allows two parties to execute neural network inference without revealing either party's data. Delphi approaches the problem by simultaneously co-designing cryptography and machine learning. We first design a hybrid cryptographic protocol that improves upon the communication and computation costs over prior work. Second, we develop a planner that automatically generates neural network architecture configurations that navigate the performance-accuracy trade-offs of our hybrid protocol. Together, these techniques allow us to achieve a 22x improvement in online prediction latency compared to the state-of-the-art prior work.