Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms

Joohyung Jeon; Junhui Kim; Joongheon Kim; Kwangsoo Kim; Aziz Mohaisen; Jong Kook Kim

doi:10.1109/DSN-S.2019.00007

Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms

Joohyung Jeon, Junhui Kim, Joongheon Kim, Kwangsoo Kim, Aziz Mohaisen, Jong Kook Kim

School of Electrical Engineering

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

7 Citations (Scopus)

Abstract

This paper proposes a distributed deep learning framework for privacy-preserving medical data training. In order to avoid patients' data leakage in medical platforms, the hidden layers in the deep learning framework are separated and where the first layer is kept in platform and others layers are kept in a centralized server. Whereas keeping the original patients' data in local platforms maintain their privacy, utilizing the server for subsequent layers improves learning performance by using all data from each platform during training.

Original language	English
Title of host publication	Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3-4
Number of pages	2
ISBN (Electronic)	9781728130286
DOIs	https://doi.org/10.1109/DSN-S.2019.00007
Publication status	Published - 2019 Jun
Event	49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019 - Portland, United States Duration: 2019 Jun 24 → 2019 Jun 27

Publication series

Name	Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019

Conference

Conference	49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019
Country	United States
City	Portland
Period	19/6/24 → 19/6/27

Keywords

Deep Learning
Medical Big Data
Privacy Preserving

ASJC Scopus subject areas

Safety, Risk, Reliability and Quality
Information Systems
Information Systems and Management
Computer Networks and Communications

Access to Document

10.1109/DSN-S.2019.00007

Fingerprint Dive into the research topics of 'Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms'. Together they form a unique fingerprint.

Cite this

Jeon, J., Kim, J., Kim, J., Kim, K., Mohaisen, A., & Kim, J. K. (2019). Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms. In Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019 (pp. 3-4). [8805784] (Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DSN-S.2019.00007

Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms. / Jeon, Joohyung; Kim, Junhui; Kim, Joongheon; Kim, Kwangsoo; Mohaisen, Aziz; Kim, Jong Kook.

Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 3-4 8805784 (Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019).

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

Jeon, J, Kim, J, Kim, J, Kim, K, Mohaisen, A & Kim, JK 2019, Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms. in Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019., 8805784, Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019, Institute of Electrical and Electronics Engineers Inc., pp. 3-4, 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019, Portland, United States, 19/6/24. https://doi.org/10.1109/DSN-S.2019.00007

Jeon J, Kim J, Kim J, Kim K, Mohaisen A, Kim JK. Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms. In Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 3-4. 8805784. (Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019). https://doi.org/10.1109/DSN-S.2019.00007

Jeon, Joohyung ; Kim, Junhui ; Kim, Joongheon ; Kim, Kwangsoo ; Mohaisen, Aziz ; Kim, Jong Kook. / Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms. Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 3-4 (Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019).

@inproceedings{91b4b3b1d75a429b9df630ff9ee03e5e,

title = "Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms",

abstract = "This paper proposes a distributed deep learning framework for privacy-preserving medical data training. In order to avoid patients' data leakage in medical platforms, the hidden layers in the deep learning framework are separated and where the first layer is kept in platform and others layers are kept in a centralized server. Whereas keeping the original patients' data in local platforms maintain their privacy, utilizing the server for subsequent layers improves learning performance by using all data from each platform during training.",

keywords = "Deep Learning, Medical Big Data, Privacy Preserving",

author = "Joohyung Jeon and Junhui Kim and Joongheon Kim and Kwangsoo Kim and Aziz Mohaisen and Kim, {Jong Kook}",

note = "Funding Information: ACKNOWLEDGMENT This work was supported by IITP (2017-0-00068 and 2018-0-00170) and also by National Research Foundation of Korea (2016R1C1B1015406 and 2017R1A4A1015675). J. Kim is a corresponding author (e-mail: joongheon@gmail.com).; 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019 ; Conference date: 24-06-2019 Through 27-06-2019",

year = "2019",

month = jun,

doi = "10.1109/DSN-S.2019.00007",

language = "English",

series = "Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019",

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

pages = "3--4",

booktitle = "Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019",

}

TY - GEN

T1 - Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms

AU - Jeon, Joohyung

AU - Kim, Junhui

AU - Kim, Joongheon

AU - Kim, Kwangsoo

AU - Mohaisen, Aziz

AU - Kim, Jong Kook

N1 - Funding Information: ACKNOWLEDGMENT This work was supported by IITP (2017-0-00068 and 2018-0-00170) and also by National Research Foundation of Korea (2016R1C1B1015406 and 2017R1A4A1015675). J. Kim is a corresponding author (e-mail: joongheon@gmail.com).

PY - 2019/6

Y1 - 2019/6

N2 - This paper proposes a distributed deep learning framework for privacy-preserving medical data training. In order to avoid patients' data leakage in medical platforms, the hidden layers in the deep learning framework are separated and where the first layer is kept in platform and others layers are kept in a centralized server. Whereas keeping the original patients' data in local platforms maintain their privacy, utilizing the server for subsequent layers improves learning performance by using all data from each platform during training.

AB - This paper proposes a distributed deep learning framework for privacy-preserving medical data training. In order to avoid patients' data leakage in medical platforms, the hidden layers in the deep learning framework are separated and where the first layer is kept in platform and others layers are kept in a centralized server. Whereas keeping the original patients' data in local platforms maintain their privacy, utilizing the server for subsequent layers improves learning performance by using all data from each platform during training.

KW - Deep Learning

KW - Medical Big Data

KW - Privacy Preserving

UR - http://www.scopus.com/inward/record.url?scp=85072042060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072042060&partnerID=8YFLogxK

U2 - 10.1109/DSN-S.2019.00007

DO - 10.1109/DSN-S.2019.00007

M3 - Conference contribution

AN - SCOPUS:85072042060

T3 - Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019

SP - 3

EP - 4

BT - Proceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019

Y2 - 24 June 2019 through 27 June 2019

ER -

Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this