Presentation 2017-12-21
A Study of Decentralization for Data Mining System Implemented with Fully Homomorphic Encryption
Yuri Yamamoto, Masato Oguchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For promoting utilization of big data, outsourcing systems have been proposed in which transaction data such as purchase history of each company are stored and analyzed. In the system, third parties receive the data and execute calculations for data mining. From the viewpoint of privacy protection, the data will need to be concealed by an encryption. Therefore, in recent years, studies of the secure outsourcing systems utilizing fully homomorphic encryption (FHE) have increased. Since FHE is a cipher method that supports both the addition and multiplication operations of ciphertexts, it can make the system to calculate statistics in keeping the data encrypted. In previous research, a client/server system was proposed for data mining using FHE. The authors also improved the query and calculation algorithms for preparation to take more advanced statistics in the future. However, since the computational complexity of operations using FHE is high, an extremely long run time on the server side needs to be shortened. In this study, we proposed the decentralized system to divide tasks on the server side by item sets for the calculation of the Apriori algorithm and discussed the future tasks for further acceleration.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Fully Homomorphic Encryption / Data Mining / Apriori algorithm / Decentralized System
Paper # MoNA2017-37
Date of Issue 2017-12-14 (MoNA)

Conference Information
Committee MoNA
Conference Date 2017/12/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Ochanomizu University
Topics (in Japanese) (See Japanese page)
Topics (in English) Cloud computing, Big data, Wireless network, etc.
Chair Ryoichi Shinkuma(Kyoto Univ.)
Vice Chair Shigeaki Tagashira(Kansai Univ.) / Gen Kitagata(Tohoku Univ.)
Secretary Shigeaki Tagashira(Kyushu Univ.) / Gen Kitagata(NTT)
Assistant Takayuki Nishio(Kyoto Univ.) / Takato Saito(NTT)

Paper Information
Registration To Technical Committee on Mobile Network and Applications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Decentralization for Data Mining System Implemented with Fully Homomorphic Encryption
Sub Title (in English)
Keyword(1) Fully Homomorphic Encryption
Keyword(2) Data Mining
Keyword(3) Apriori algorithm
Keyword(4) Decentralized System
1st Author's Name Yuri Yamamoto
1st Author's Affiliation Ochanomizu University(Ochanomizu Univ.)
2nd Author's Name Masato Oguchi
2nd Author's Affiliation Ochanomizu University(Ochanomizu Univ.)
Date 2017-12-21
Paper # MoNA2017-37
Volume (vol) vol.117
Number (no) MoNA-371
Page pp.pp.49-53(MoNA),
#Pages 5
Date of Issue 2017-12-14 (MoNA)