Towards practical homomorphic email filtering: A hardware-accelerated secure naïve Bayesian filter

Song Bian; Masayuki Hiromoto; Takashi Sato

doi:10.1145/3287624.3287699

Towards practical homomorphic email filtering: A hardware-accelerated secure naïve Bayesian filter

Song Bian
, Masayuki Hiromoto
, Takashi Sato

Kyoto University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

A secure version of the naïve Bayesian filter (NBF) is proposed utilizing partially homomorphic encryption (PHE) scheme. SNBF can be implemented with only the additive homomorphism from the Paillier system, and we derive new techniques to reduce the computational cost of PHE-based SNBF. In the experiment, we implemented SNBF both in software and hardware. Compared to the best existing PHE scheme, we achieved 1,200x (resp., 398,840x) runtime reduction in the CPU (resp., ASIC) implementations, with additional 1,919x power reduction on the designated hardware multiplier. Our hardware implementation is able to classify an average-length email in 0.5 s, making it one of the most practical NBF schemes to date.

Original language	English
Title of host publication	ASP-DAC 2019 - 24th Asia and South Pacific Design Automation Conference
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	621-626
Number of pages	6
ISBN (Electronic)	9781450360074
DOIs	https://doi.org/10.1145/3287624.3287699
State	Published - 21 Jan 2019
Externally published	Yes
Event	24th Asia and South Pacific Design Automation Conference, ASPDAC 2019 - Tokyo, Japan Duration: 21 Jan 2019 → 24 Jan 2019

Publication series

Name	Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC

Conference

Conference	24th Asia and South Pacific Design Automation Conference, ASPDAC 2019
Country/Territory	Japan
City	Tokyo
Period	21/01/19 → 24/01/19

Access to Document

10.1145/3287624.3287699

Cite this

Bian, S., Hiromoto, M., & Sato, T. (2019). Towards practical homomorphic email filtering: A hardware-accelerated secure naïve Bayesian filter. In ASP-DAC 2019 - 24th Asia and South Pacific Design Automation Conference (pp. 621-626). (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/3287624.3287699

Bian, Song ; Hiromoto, Masayuki ; Sato, Takashi. / Towards practical homomorphic email filtering : A hardware-accelerated secure naïve Bayesian filter. ASP-DAC 2019 - 24th Asia and South Pacific Design Automation Conference. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 621-626 (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC).

@inproceedings{3540627a606c47f291754b5daaeb88b7,

title = "Towards practical homomorphic email filtering: A hardware-accelerated secure na{\"i}ve Bayesian filter",

abstract = "A secure version of the na{\"i}ve Bayesian filter (NBF) is proposed utilizing partially homomorphic encryption (PHE) scheme. SNBF can be implemented with only the additive homomorphism from the Paillier system, and we derive new techniques to reduce the computational cost of PHE-based SNBF. In the experiment, we implemented SNBF both in software and hardware. Compared to the best existing PHE scheme, we achieved 1,200x (resp., 398,840x) runtime reduction in the CPU (resp., ASIC) implementations, with additional 1,919x power reduction on the designated hardware multiplier. Our hardware implementation is able to classify an average-length email in 0.5 s, making it one of the most practical NBF schemes to date.",

author = "Song Bian and Masayuki Hiromoto and Takashi Sato",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 24th Asia and South Pacific Design Automation Conference, ASPDAC 2019 ; Conference date: 21-01-2019 Through 24-01-2019",

year = "2019",

month = jan,

day = "21",

doi = "10.1145/3287624.3287699",

language = "英语",

series = "Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "621--626",

booktitle = "ASP-DAC 2019 - 24th Asia and South Pacific Design Automation Conference",

address = "美国",

}

Bian, S, Hiromoto, M & Sato, T 2019, Towards practical homomorphic email filtering: A hardware-accelerated secure naïve Bayesian filter. in ASP-DAC 2019 - 24th Asia and South Pacific Design Automation Conference. Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC, Institute of Electrical and Electronics Engineers Inc., pp. 621-626, 24th Asia and South Pacific Design Automation Conference, ASPDAC 2019, Tokyo, Japan, 21/01/19. https://doi.org/10.1145/3287624.3287699

Towards practical homomorphic email filtering: A hardware-accelerated secure naïve Bayesian filter. / Bian, Song; Hiromoto, Masayuki; Sato, Takashi.
ASP-DAC 2019 - 24th Asia and South Pacific Design Automation Conference. Institute of Electrical and Electronics Engineers Inc., 2019. p. 621-626 (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Towards practical homomorphic email filtering

T2 - 24th Asia and South Pacific Design Automation Conference, ASPDAC 2019

AU - Bian, Song

AU - Hiromoto, Masayuki

AU - Sato, Takashi

PY - 2019/1/21

Y1 - 2019/1/21

N2 - A secure version of the naïve Bayesian filter (NBF) is proposed utilizing partially homomorphic encryption (PHE) scheme. SNBF can be implemented with only the additive homomorphism from the Paillier system, and we derive new techniques to reduce the computational cost of PHE-based SNBF. In the experiment, we implemented SNBF both in software and hardware. Compared to the best existing PHE scheme, we achieved 1,200x (resp., 398,840x) runtime reduction in the CPU (resp., ASIC) implementations, with additional 1,919x power reduction on the designated hardware multiplier. Our hardware implementation is able to classify an average-length email in 0.5 s, making it one of the most practical NBF schemes to date.

AB - A secure version of the naïve Bayesian filter (NBF) is proposed utilizing partially homomorphic encryption (PHE) scheme. SNBF can be implemented with only the additive homomorphism from the Paillier system, and we derive new techniques to reduce the computational cost of PHE-based SNBF. In the experiment, we implemented SNBF both in software and hardware. Compared to the best existing PHE scheme, we achieved 1,200x (resp., 398,840x) runtime reduction in the CPU (resp., ASIC) implementations, with additional 1,919x power reduction on the designated hardware multiplier. Our hardware implementation is able to classify an average-length email in 0.5 s, making it one of the most practical NBF schemes to date.

UR - https://www.scopus.com/pages/publications/85061155215

U2 - 10.1145/3287624.3287699

DO - 10.1145/3287624.3287699

M3 - 会议稿件

AN - SCOPUS:85061155215

T3 - Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC

SP - 621

EP - 626

BT - ASP-DAC 2019 - 24th Asia and South Pacific Design Automation Conference

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 21 January 2019 through 24 January 2019

ER -

Bian S, Hiromoto M, Sato T. Towards practical homomorphic email filtering: A hardware-accelerated secure naïve Bayesian filter. In ASP-DAC 2019 - 24th Asia and South Pacific Design Automation Conference. Institute of Electrical and Electronics Engineers Inc. 2019. p. 621-626. (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC). doi: 10.1145/3287624.3287699

Towards practical homomorphic email filtering: A hardware-accelerated secure naïve Bayesian filter

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this