Learnable audio encryption for untrusted outsourcing machine learning services

Po Wen Chi; Pin Hsin Hsiao

doi:10.1109/AsiaJCIS.2019.00012

Learnable audio encryption for untrusted outsourcing machine learning services

Po Wen Chi, Pin Hsin Hsiao

Department of Computer Science and Information Engineering

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

1 Citation (Scopus)

Abstract

Applying machine learning to problems has become an avoidable trend. With the help of machine learning techniques, people can make predictions more accurately and can get more benefits. However, the machine learning technique relies on training from lots of data. That is, data should be open to the machine learning service provider. Considering the user privacy issue, the release of user data is not acceptable. In this paper, we propose an approach to take care both the machine learning feature and the data privacy. We focus on audio data and propose an audio encryption technique to keep audio data credential. In the meantime, we make the encrypted audio be able to be trained though machine learning service providers.

Original language	English
Title of host publication	Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	151-156
Number of pages	6
ISBN (Electronic)	9781728125565
DOIs	https://doi.org/10.1109/AsiaJCIS.2019.00012
Publication status	Published - 2019 Aug
Event	14th Annual Asia Joint Conference on Information Security, AsiaJCIS 2019 - Kobe, Japan Duration: 2019 Aug 1 → 2019 Aug 2

Publication series

Name	Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019

Conference

Conference	14th Annual Asia Joint Conference on Information Security, AsiaJCIS 2019
Country/Territory	Japan
City	Kobe
Period	2019/08/01 → 2019/08/02

Keywords

Audio encryption
Learnable encryption
Machine learning

ASJC Scopus subject areas

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

Access to Document

10.1109/AsiaJCIS.2019.00012

Cite this

Chi, P. W., & Hsiao, P. H. (2019). Learnable audio encryption for untrusted outsourcing machine learning services. In Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019 (pp. 151-156). Article 8826816 (Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AsiaJCIS.2019.00012

Learnable audio encryption for untrusted outsourcing machine learning services. / Chi, Po Wen; Hsiao, Pin Hsin.
Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 151-156 8826816 (Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019).

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

Chi, PW & Hsiao, PH 2019, Learnable audio encryption for untrusted outsourcing machine learning services. in Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019., 8826816, Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 151-156, 14th Annual Asia Joint Conference on Information Security, AsiaJCIS 2019, Kobe, Japan, 2019/08/01. https://doi.org/10.1109/AsiaJCIS.2019.00012

Chi PW, Hsiao PH. Learnable audio encryption for untrusted outsourcing machine learning services. In Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 151-156. 8826816. (Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019). doi: 10.1109/AsiaJCIS.2019.00012

@inproceedings{767ca09f151a45389624ae1ec43911d6,

title = "Learnable audio encryption for untrusted outsourcing machine learning services",

abstract = "Applying machine learning to problems has become an avoidable trend. With the help of machine learning techniques, people can make predictions more accurately and can get more benefits. However, the machine learning technique relies on training from lots of data. That is, data should be open to the machine learning service provider. Considering the user privacy issue, the release of user data is not acceptable. In this paper, we propose an approach to take care both the machine learning feature and the data privacy. We focus on audio data and propose an audio encryption technique to keep audio data credential. In the meantime, we make the encrypted audio be able to be trained though machine learning service providers.",

keywords = "Audio encryption, Learnable encryption, Machine learning",

author = "Chi, {Po Wen} and Hsiao, {Pin Hsin}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 14th Annual Asia Joint Conference on Information Security, AsiaJCIS 2019 ; Conference date: 01-08-2019 Through 02-08-2019",

year = "2019",

month = aug,

doi = "10.1109/AsiaJCIS.2019.00012",

language = "English",

series = "Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019",

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

pages = "151--156",

booktitle = "Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019",

}

TY - GEN

T1 - Learnable audio encryption for untrusted outsourcing machine learning services

AU - Chi, Po Wen

AU - Hsiao, Pin Hsin

PY - 2019/8

Y1 - 2019/8

N2 - Applying machine learning to problems has become an avoidable trend. With the help of machine learning techniques, people can make predictions more accurately and can get more benefits. However, the machine learning technique relies on training from lots of data. That is, data should be open to the machine learning service provider. Considering the user privacy issue, the release of user data is not acceptable. In this paper, we propose an approach to take care both the machine learning feature and the data privacy. We focus on audio data and propose an audio encryption technique to keep audio data credential. In the meantime, we make the encrypted audio be able to be trained though machine learning service providers.

AB - Applying machine learning to problems has become an avoidable trend. With the help of machine learning techniques, people can make predictions more accurately and can get more benefits. However, the machine learning technique relies on training from lots of data. That is, data should be open to the machine learning service provider. Considering the user privacy issue, the release of user data is not acceptable. In this paper, we propose an approach to take care both the machine learning feature and the data privacy. We focus on audio data and propose an audio encryption technique to keep audio data credential. In the meantime, we make the encrypted audio be able to be trained though machine learning service providers.

KW - Audio encryption

KW - Learnable encryption

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85073475631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073475631&partnerID=8YFLogxK

U2 - 10.1109/AsiaJCIS.2019.00012

DO - 10.1109/AsiaJCIS.2019.00012

M3 - Conference contribution

AN - SCOPUS:85073475631

T3 - Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019

SP - 151

EP - 156

BT - Proceedings - 2019 14th Asia Joint Conference on Information Security, AsiaJCIS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th Annual Asia Joint Conference on Information Security, AsiaJCIS 2019

Y2 - 1 August 2019 through 2 August 2019

ER -

Learnable audio encryption for untrusted outsourcing machine learning services

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this