PMID- 33374259
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20210104
LR  - 20240330
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 21
IP  - 1
DP  - 2020 Dec 24
TI  - GAN-Based Differential Private Image Privacy Protection Framework for the 
      Internet of Multimedia Things.
LID - 10.3390/s21010058 [doi]
LID - 58
AB  - 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.
FAU - Yu, Jinao
AU  - Yu J
AUID- ORCID: 0000-0002-7337-9029
AD  - School of Space Information, Space Engineering University, Beijing 101416, China.
FAU - Xue, Hanyu
AU  - Xue H
AD  - School of Computer Science, University of Technology Sydney, Sydney, NSW 2007, 
      Australia.
FAU - Liu, Bo
AU  - Liu B
AD  - School of Computer Science, University of Technology Sydney, Sydney, NSW 2007, 
      Australia.
FAU - Wang, Yu
AU  - Wang Y
AUID- ORCID: 0000-0002-9807-2293
AD  - Institute of Artificial Intelligence and Blockchain, Guangzhou University, 
      Guangzhou 510006, China.
FAU - Zhu, Shibing
AU  - Zhu S
AD  - School of Space Information, Space Engineering University, Beijing 101416, China.
FAU - Ding, Ming
AU  - Ding M
AD  - Data61, CSIRO, Sydney, NSW 2015, Australia.
LA  - eng
GR  - DXZT-JC-ZZ2017-005/Science and Technology on Complex Electronic Simulation 
      Laboratory Foundation/
GR  - 61802080/National Natural Science Foundation of China/
GR  - 201831827/Education Bureau of Guangzhou Municipality Higher Education Research 
      Project/
GR  - RQ2020085/Guangzhou University Research Project/
PT  - Journal Article
DEP - 20201224
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
PMC - PMC7795307
OTO - NOTNLM
OT  - Internet of Multimedia Things (IoMT)
OT  - deep learning
OT  - differential privacy
OT  - generative adversarial network
OT  - image privacy
OT  - object detection
COIS- The authors declare no conflict of interest.
EDAT- 2020/12/31 06:00
MHDA- 2020/12/31 06:01
PMCR- 2020/12/24
CRDT- 2020/12/30 01:00
PHST- 2020/11/24 00:00 [received]
PHST- 2020/12/14 00:00 [revised]
PHST- 2020/12/19 00:00 [accepted]
PHST- 2020/12/30 01:00 [entrez]
PHST- 2020/12/31 06:00 [pubmed]
PHST- 2020/12/31 06:01 [medline]
PHST- 2020/12/24 00:00 [pmc-release]
AID - s21010058 [pii]
AID - sensors-21-00058 [pii]
AID - 10.3390/s21010058 [doi]
PST - epublish
SO  - Sensors (Basel). 2020 Dec 24;21(1):58. doi: 10.3390/s21010058.