中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 重庆绿色智能技术研究院
  3. 中国科学院重庆绿色智能技术研究院
cuSCNN: A Secure and Batch-Processing Framework for Privacy-Preserving Convolutional Neural Network Prediction on GPU

文献类型：期刊论文

作者Bai, Yanan2,3; Liu, Quanliang1,3; Wu, Wenyuan2; Feng, Yong2
刊名FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
出版日期2021-12-23
卷号15页码:13
关键词privacy-preserving convolutional neural network homomorphic encryption GPU computation deep learning cloud computing
DOI10.3389/fncom.2021.799977
通讯作者Wu, Wenyuan(wuwenyuan@cigit.ac.cn)
英文摘要The emerging topic of privacy-preserving deep learning as a service has attracted increasing attention in recent years, which focuses on building an efficient and practical neural network prediction framework to secure client and model-holder data privately on the cloud. In such a task, the time cost of performing the secure linear layers is expensive, where matrix multiplication is the atomic operation. Most existing mix-based solutions heavily emphasized employing BGV-based homomorphic encryption schemes to secure the linear layer on the CPU platform. However, they suffer an efficiency and energy loss when dealing with a larger-scale dataset, due to the complicated encoded methods and intractable ciphertext operations. To address it, we propose cuSCNN, a secure and efficient framework to perform the privacy prediction task of a convolutional neural network (CNN), which can flexibly perform on the GPU platform. Its main idea is 2-fold: (1) To avoid the trivia and complicated homomorphic matrix computations brought by BGV-based solutions, it adopts GSW-based homomorphic matrix encryption to efficiently enable the linear layers of CNN, which is a naive method to secure matrix computation operations. (2) To improve the computation efficiency on GPU, a hybrid optimization approach based on CUDA (Compute Unified Device Architecture) has been proposed to improve the parallelism level and memory access speed when performing the matrix multiplication on GPU. Extensive experiments are conducted on industrial datasets and have shown the superior performance of the proposed cuSCNN framework in terms of runtime and power consumption compared to the other frameworks.
资助项目National Key Research and Development Project[2020YFA0712303] ; Chongqing Research Program[cstc2019yszx-jcyjX0003] ; Chongqing Research Program[cstc2020yszx-jcyjX0005] ; Chongqing Research Program[cstc2021yszx-jcyjX0004] ; Guizhou Science and Technology Program[[2020]4Y056] ; NSFC[11771421] ; Youth Innovation Promotion Association of CAS[2018419] ; Key Cooperation Project of Chongqing Municipal Education Commission[HZ2021017] ; Key Cooperation Project of Chongqing Municipal Education Commission[HZ2021008] ; CAS Light of West China Program
WOS研究方向Mathematical & Computational Biology ; Neurosciences & Neurology
语种英语
WOS记录号WOS:000743513500001
出版者FRONTIERS MEDIA SA
源URL[http://119.78.100.138/handle/2HOD01W0/14896]  
专题中国科学院重庆绿色智能技术研究院
通讯作者Wu, Wenyuan
作者单位1.Univ Chinese Acad Sci, Chongqing Sch, Chongqing, Peoples R China
2.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing Key Lab Automated Reasoning & Cognit, Chongqing, Peoples R China
3.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Bai, Yanan,Liu, Quanliang,Wu, Wenyuan,et al. cuSCNN: A Secure and Batch-Processing Framework for Privacy-Preserving Convolutional Neural Network Prediction on GPU[J]. FRONTIERS IN COMPUTATIONAL NEUROSCIENCE,2021,15:13.
APA Bai, Yanan,Liu, Quanliang,Wu, Wenyuan,&Feng, Yong.(2021).cuSCNN: A Secure and Batch-Processing Framework for Privacy-Preserving Convolutional Neural Network Prediction on GPU.FRONTIERS IN COMPUTATIONAL NEUROSCIENCE,15,13.
MLA Bai, Yanan,et al."cuSCNN: A Secure and Batch-Processing Framework for Privacy-Preserving Convolutional Neural Network Prediction on GPU".FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 15(2021):13.

入库方式： OAI收割

来源：重庆绿色智能技术研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。