TOWARD SECURE IMAGE DENOISING: A MACHINE LEARNING BASED REALIZATION

Yifeng Zheng; Cong Wang; Jiantao Zhou

doi:10.1109/ICASSP.2018.8462073

TOWARD SECURE IMAGE DENOISING: A MACHINE LEARNING BASED REALIZATION

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

Image denoising via machine learning techniques, particularly neural networks, has been shown to achieve state-of-the-art performance. However, in practice security and privacy issues undesirably arise in applying a trained machine learning model to image denoising. In this paper, we propose a system framework that enables the owner of a trained machine learning model to provide secure image denoising service to an authorized user, via the aid of cloud computing. Our framework ensures that the cloud server learns nothing about the model and the user's images, while the user learns nothing about the model except denoised images. Experiments are conducted for performance evaluation, and the results show that our design can achieve denoising quality close to that in the plaintext domain. For future work, we plan to explore various directions for optimizing the runtime performance.

Original language	English
Title of host publication	2018 IEEE International Conference on Acoustics, Speech, and Signal Processing
Subtitle of host publication	Proceedings
Publisher	IEEE
Pages	6936-6940
ISBN (Electronic)	9781538646588
ISBN (Print)	9781538646595
DOIs	https://doi.org/10.1109/ICASSP.2018.8462073
Publication status	Published - Apr 2018
Event	2018 IEEE International Conference on Accoustics, Speech and Signal Processing (IEEE ICASSP 2018) - Calgary, Canada Duration: 15 Apr 2018 → 20 Apr 2018 https://2018.ieeeicassp.org/Papers/PublicSessionIndex3.asp?Sessionid=1001

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2018-April
ISSN (Print)	1520-6149
ISSN (Electronic)	2379-190X

Conference

Conference	2018 IEEE International Conference on Accoustics, Speech and Signal Processing (IEEE ICASSP 2018)
Country/Territory	Canada
City	Calgary
Period	15/04/18 → 20/04/18
Internet address	https://2018.ieeeicassp.org/Papers/PublicSessionIndex3.asp?Sessionid=1001

Research Keywords

Cloud computing
Image denoising
Machine learning
Neural network
Privacy

Access Output

10.1109/ICASSP.2018.8462073

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zheng, Y., Wang, C., & Zhou, J. (2018). TOWARD SECURE IMAGE DENOISING: A MACHINE LEARNING BASED REALIZATION. In 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing: Proceedings (pp. 6936-6940). Article 8462073 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2018-April). IEEE. https://doi.org/10.1109/ICASSP.2018.8462073

@inproceedings{c6a302400cd14707be95e169cecd3c28,

title = "TOWARD SECURE IMAGE DENOISING: A MACHINE LEARNING BASED REALIZATION",

abstract = "Image denoising via machine learning techniques, particularly neural networks, has been shown to achieve state-of-the-art performance. However, in practice security and privacy issues undesirably arise in applying a trained machine learning model to image denoising. In this paper, we propose a system framework that enables the owner of a trained machine learning model to provide secure image denoising service to an authorized user, via the aid of cloud computing. Our framework ensures that the cloud server learns nothing about the model and the user's images, while the user learns nothing about the model except denoised images. Experiments are conducted for performance evaluation, and the results show that our design can achieve denoising quality close to that in the plaintext domain. For future work, we plan to explore various directions for optimizing the runtime performance.",

keywords = "Cloud computing, Image denoising, Machine learning, Neural network, Privacy",

author = "Yifeng Zheng and Cong Wang and Jiantao Zhou",

year = "2018",

month = apr,

doi = "10.1109/ICASSP.2018.8462073",

language = "English",

isbn = "9781538646595",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "IEEE",

pages = "6936--6940",

booktitle = "2018 IEEE International Conference on Acoustics, Speech, and Signal Processing",

address = "United States",

note = "2018 IEEE International Conference on Accoustics, Speech and Signal Processing (IEEE ICASSP 2018) ; Conference date: 15-04-2018 Through 20-04-2018",

url = "https://2018.ieeeicassp.org/Papers/PublicSessionIndex3.asp?Sessionid=1001",

}

Zheng, Y , Wang, C & Zhou, J 2018, TOWARD SECURE IMAGE DENOISING: A MACHINE LEARNING BASED REALIZATION. in 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing: Proceedings., 8462073, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2018-April, IEEE, pp. 6936-6940, 2018 IEEE International Conference on Accoustics, Speech and Signal Processing (IEEE ICASSP 2018), Calgary, Alberta, Canada, 15/04/18. https://doi.org/10.1109/ICASSP.2018.8462073

TOWARD SECURE IMAGE DENOISING: A MACHINE LEARNING BASED REALIZATION. / Zheng, Yifeng ; Wang, Cong; Zhou, Jiantao.
2018 IEEE International Conference on Acoustics, Speech, and Signal Processing: Proceedings. IEEE, 2018. p. 6936-6940 8462073 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2018-April).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - TOWARD SECURE IMAGE DENOISING

T2 - 2018 IEEE International Conference on Accoustics, Speech and Signal Processing (IEEE ICASSP 2018)

AU - Zheng, Yifeng

AU - Wang, Cong

AU - Zhou, Jiantao

PY - 2018/4

Y1 - 2018/4

N2 - Image denoising via machine learning techniques, particularly neural networks, has been shown to achieve state-of-the-art performance. However, in practice security and privacy issues undesirably arise in applying a trained machine learning model to image denoising. In this paper, we propose a system framework that enables the owner of a trained machine learning model to provide secure image denoising service to an authorized user, via the aid of cloud computing. Our framework ensures that the cloud server learns nothing about the model and the user's images, while the user learns nothing about the model except denoised images. Experiments are conducted for performance evaluation, and the results show that our design can achieve denoising quality close to that in the plaintext domain. For future work, we plan to explore various directions for optimizing the runtime performance.

AB - Image denoising via machine learning techniques, particularly neural networks, has been shown to achieve state-of-the-art performance. However, in practice security and privacy issues undesirably arise in applying a trained machine learning model to image denoising. In this paper, we propose a system framework that enables the owner of a trained machine learning model to provide secure image denoising service to an authorized user, via the aid of cloud computing. Our framework ensures that the cloud server learns nothing about the model and the user's images, while the user learns nothing about the model except denoised images. Experiments are conducted for performance evaluation, and the results show that our design can achieve denoising quality close to that in the plaintext domain. For future work, we plan to explore various directions for optimizing the runtime performance.

KW - Cloud computing

KW - Image denoising

KW - Machine learning

KW - Neural network

KW - Privacy

UR - http://www.scopus.com/inward/record.url?scp=85054265758&partnerID=8YFLogxK

UR - http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000446384607019

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85054265758&origin=recordpage

U2 - 10.1109/ICASSP.2018.8462073

DO - 10.1109/ICASSP.2018.8462073

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781538646595

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 6936

EP - 6940

BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing

PB - IEEE

Y2 - 15 April 2018 through 20 April 2018

ER -

TOWARD SECURE IMAGE DENOISING: A MACHINE LEARNING BASED REALIZATION

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this