La Trobe
1155199_Yu,J_2021.pdf (12.74 MB)

Gan-based Differential Private Image Privacy Protection Framework for the Internet of Multimedia Things

Download (12.74 MB)
journal contribution
posted on 13.04.2021, 02:18 by J Yu, H Xue, Bo Liu, Y Wang, S Zhu, M Ding
With the development of the Internet of Multimedia Things (IoMT), an increasing amount of image data is collected by various multimedia devices, such as smartphones, cameras, and drones. This massive number of images are widely used in each field of IoMT, which presents substantial challenges for privacy preservation. In this paper, we propose a new image privacy protection framework in an effort to protect the sensitive personal information contained in images collected by IoMT devices. We aim to use deep neural network techniques to identify the privacy-sensitive content in images, and then protect it with the synthetic content generated by generative adversarial networks (GANs) with differential privacy (DP). Our experiment results show that the proposed framework can effectively protect users’ privacy while maintaining image utility.

Funding

This research was funded by the Science and Technology on Complex Electronic Simulation Laboratory Foundation under grant Number DXZT-JC-ZZ2017-005, the National Natural Science Foundation of China under grant Number 61802080, the Education Bureau of Guangzhou Municipality Higher Education Research Project under grant Number 201831827 and the Guangzhou University Research Project under grant Number RQ2020085.

History

Publication Date

01/01/2021

Journal

Sensors

Volume

21

Issue

1

Article Number

ARTN 58

Pagination

(p. 1-21)

Publisher

MDPI

ISSN

1424-8220

Rights Statement

The Author reserves all moral rights over the deposited text and must be credited if any re-use occurs. Documents deposited in OPAL are the Open Access versions of outputs published elsewhere. Changes resulting from the publishing process may therefore not be reflected in this document. The final published version may be obtained via the publisher’s DOI. Please note that additional copyright and access restrictions may apply to the published version.

Licence

Exports