ReDCrypt
ReDCrypt
复制标题
重新加密
DOI：
--
复制
发表时间：
2018
影响因子：
2.3
通讯作者：
F. Koushanfar
中科院分区：
文献类型：
--
作者：
B. Rouhani;S. Hussain;K. Lauter;F. Koushanfar
人工智能（AI）越来越多地纳入云业务，以提高使用AI的功能（例如，准确性）。此类应用程序的示例包括客户拥有潜在敏感的私人信息，例如医疗记录，财务数据和/或位置。首先，可重新配置的硬件加速框架，使RedCrypt中深度学习模型的隐私推理非常适合流式传输（又称实时AI）设置，在其中客户需要动态分析其数据与先前的工作不同，不必排队样品以满足一定的批次。执行RedCrypt中的隐私计算（交互式）计算。我们在FPGA上为隐私敏感阶段设计了高通量和效率的实现。将RedCrypt集成到任何深度学习框架中。
Artificial Intelligence (AI) is increasingly incorporated into the cloud business in order to improve the functionality (e.g., accuracy) of the service. The adoption of AI as a cloud service raises serious privacy concerns in applications where the risk of data leakage is not acceptable. Examples of such applications include scenarios where clients hold potentially sensitive private information such as medical records, financial data, and/or location. This article proposes ReDCrypt, the first reconfigurable hardware-accelerated framework that empowers privacy-preserving inference of deep learning models in cloud servers. ReDCrypt is well-suited for streaming (a.k.a., real-time AI) settings where clients need to dynamically analyze their data as it is collected over time without having to queue the samples to meet a certain batch size. Unlike prior work, ReDCrypt neither requires to change how AI models are trained nor relies on two non-colluding servers to perform. The privacy-preserving computation in ReDCrypt is executed using Yao’s Garbled Circuit (GC) protocol. We break down the deep learning inference task into two phases: (i) privacy-insensitive (local) computation, and (ii) privacy-sensitive (interactive) computation. We devise a high-throughput and power-efficient implementation of GC protocol on FPGA for the privacy-sensitive phase. ReDCrypt’s accompanying API provides support for seamless integration of ReDCrypt into any deep learning framework. Proof-of-concept evaluations for different DL applications demonstrate up to 57-fold higher throughput per core compared to the best prior solution with no drop in the accuracy.