PCNNCEC: Efficient and Privacy-Preserving Convolutional Neural Network Inference Based on Cloud-Edge-Client Collaboration

ASIA unversity > 管理學院 > 經營管理學系 > 期刊論文 > Item 310904400/115571

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://asiair.asia.edu.tw/ir/handle/310904400/115571

题名:	PCNNCEC: Efficient and Privacy-Preserving Convolutional Neural Network Inference Based on Cloud-Edge-Client Collaboration
作者:	Wang, Jing;Wang, Jing;He, Debiao;He, Debiao;Cast, Aniello;Castiglione, Aniello;Bhoosha, Brij;Gupta, Brij Bhooshan;Ka, Marimuthu;Marimuthu Karuppiah;Wu, Libing;Wu, Libing
贡献者:	資訊電機學院資訊工程學系
关键词:	Protocols , Computational modeling , Industrial Internet of Things , Cryptography , Servers , Convolutional neural networks , Machine learning
日期:	2022-05-01
上传时间:	2023-03-29 02:49:36 (UTC+0)
出版者:	亞洲大學
摘要:	Deploying convolutional neural network (CNN) inference on resource-constrained devices remains a remarkable challenge for industrial Internet of Things (IIoT). Although the cloud computing shows great promise in machine learning training and prediction, outsourcing data to remote cloud always incurs privacy risk and high latency. Therefore, we design a new framework for efficient and privacy-preserving CNN inference based on cloud-edge-client collaboration (namedPCNNCEC). In PCNNCEC, the model of cloud and the data of client in IIoT are split into two shares and sent to two non-colluded edge servers. By applying the arithmetic secret sharing and pre-computation of beaver's triplets, the two edge servers can jointly calculate the predicting results without learning anything about the model and data. To speed up the pre-computation of offline phase and not sacrifice security, the task of triplets generation is delegated to the cloud, so that the edge servers do not require frequent interactions to generate triplets themselves or introducing additional trusted party. The experimental results show the proposed private comparison protocol achieves a better tradeoff between low latency and high throughput, when it is compared with garbled circuit based protocols and other secret sharing based protocols. Additionally, the benchmarks conducted on realistic MNIST and CIFAR-10 datasets demonstrate that PCNNCEC costs less communication and runtime than two recently related schemes under the same security level.
显示于类别:	[經營管理學系 ] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	91	检视/开启

在ASIAIR中所有的数据项都受到原著作权保护.

数据加载中.....