Accelerator Design and Performance Modeling for Homomorphic Encrypted CNN Inference
Accelerator Design and Performance Modeling for Homomorphic Encrypted CNN Inference
复制标题
DOI：
10.1109/hpec43674.2020.9286219
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Tian Ye;R. Kannan;V. Prasanna
中科院分区：
文献类型：
--
作者：
Tian Ye;R. Kannan;V. Prasanna
云计算的快速发展带来了对数据安全和隐私的担忧。全同态加密（FHE）是一种实现数据安全的技术，允许直接对加密数据执行任意计算。特别地，FHE可以与卷积神经网络（CNN）一起使用，以对同态加密的输入数据执行推理作为服务。然而，FHE推理的高计算需求需要仔细理解各种参数（如安全级别、硬件资源和性能）之间的权衡。在本文中，我们提出了一个参数化加速器同态加密CNN推理。我们首先开发并行算法来通过FHE原语实现CNN操作。然后，我们开发了一个参数化模型来评估CNN设计的性能。该模型接受可用硬件资源和安全参数方面的输入，并输出性能估计。作为一个例子，对于具有七层CNN模型的CIFAR-10数据集上的典型图像分类任务，我们证明了一批4K加密图像可以在1秒内在以2 GHz时钟速率运行的设备上进行分类，该设备具有16 K MAC，64 MB片上内存和256 GB/s外部内存带宽。
The rapid advent of cloud computing has brought with it concerns on data security and privacy. Fully Homomorphic Encryption (FHE) is a technique for enabling data security that allows arbitrary computations to be performed directly on encrypted data. In particular, FHE can be used with convolutional neural networks (CNN) to perform inference as a service on homomorphic encrypted input data. However, the high computational demands of FHE inference require a careful understanding of the tradeoffs between various parameters such as security level, hardware resources and performance. In this paper, we propose a parameterized accelerator for homomorphic encrypted CNN inference. We first develop parallel algorithms to implement CNN operations via FHE primitives. We then develop a parameterized model to evaluate the performance of our CNN design. The model accepts inputs in terms of available hardware resources and security parameters and outputs performance estimates. As an illustration, for a typical image classification task on CIFAR-10 dataset with a seven-layer CNN model, we show that a batch of 4K encrypted images can be classified within 1 second on a device operating at 2 GHz clock rate with 16K MACs, 64 MB on-chip memory and 256 GB/s external memory bandwidth.