文章基本信息

标题：Analog Q-learning Methods for Secure Multiparty Computation
本地全文：下载
作者：Hirofumi Miyajima ; Noritaka Shigei ; Hiromi Miyajima 等
期刊名称：IAENG International Journal of Computer Science
印刷版ISSN：1819-656X
电子版ISSN：1819-9224
出版年度：2018
卷号：45
期号：4
页码：623-629
出版社：IAENG - International Association of Engineers
摘要：One problem in cloud computing system is how toconceal individual information. Although encryption technologyis one of methods to solve the problem, the computationtime required for encryption and decryption as the amountof data increases is a bottleneck. On the other hand, the secretprocessing of SMC, by reducing the amount of data processedby partitioning data, achieves confidentiality and speeding up.Compared with encryption technology, SMC can realize highspeedand secret processing, but in order to perform it manyservers are required. Therefore, an easily method using SMCand simple encryption has been proposed. Several algorithmsrelated to supervised, unsupervised and reinforcement learninghave been proposed so far as the methods of SMC on machinelearning. Since there is no learning data in reinforcementlearning, the result is obtained on the client without informingthe solution system (parameter) to any server. Algorithms for Qlearning and PS learning in digital model have been proposedso far but no results on analog model have been obtained yet.In this paper, an algorithm of Q learning in analog model isproposed. Moreover, the effectiveness of the result is shown bynumerical simulation. of this column.
关键词：cloud computing; secure multiparty computation;Q-learning; analog model