Camouflage generative adversarial network: a coverless full-image-to-image hiding

Xiyao Liu*, Ziping Ma, Xingbei Guo, Jialu Hou, Gerald Schaefer, Lei Wang, Victoria Wang, Hui Fang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

86 Downloads (Pure)

Abstract

Image hiding, one of the most important data hiding techniques, is widely used to enhance cybersecurity when transmitting multimedia data. In recent years, deep learning- based image hiding algorithms have been designed to improve the embedding capacity whilst maintaining sufficient imperceptibility to malicious eavesdroppers. These methods can hide a full-size secret image into a cover image, thus allowing full-image-to- image hiding. However, these methods suffer from a trade- off challenge to balance the possibility of detection from the container image against the recovery quality of secret image. In this paper, we propose Camouflage Generative Adversarial Network (Cam-GAN), a novel two-stage coverless full-image- to-image hiding method named, to tackle this problem. Our method offers a hiding solution through image synthesis to avoid using a modified cover image as the image hiding container and thus enhancing both image hiding imperceptibility and recovery quality of secret images. Our experimental results demonstrate that Cam-GAN outperforms state-of-the-art full-image-to-image hiding algorithms on both aspects.
Original languageEnglish
Title of host publicationProceedings of 2020 IEEE International Conference on Systems, Man and Cybernetics
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages166-172
Number of pages7
ISBN (Electronic)9781728185262
ISBN (Print)9781728185279
DOIs
Publication statusPublished - 11 Oct 2020
Event2020 IEEE International Conference on Systems, Man, and Cybernetics - Toronto, Canada
Duration: 11 Oct 202014 Oct 2020
https://www.ieeesmc.org/conferences/calendar/event/655-2020-ieee-international-conference-on-systems-man-and-cybernetics-smc

Publication series

NameIEEE Proceedings of the International Conference on Systems, Man and Cybernetics
ISSN (Print)1062-922X
ISSN (Electronic)2577-1655

Conference

Conference2020 IEEE International Conference on Systems, Man, and Cybernetics
Abbreviated titleSMC 2020
Country/TerritoryCanada
CityToronto
Period11/10/2014/10/20
Internet address

Keywords

  • Image hiding
  • Deep learning
  • generative adversarial networks
  • Image synthesis

Fingerprint

Dive into the research topics of 'Camouflage generative adversarial network: a coverless full-image-to-image hiding'. Together they form a unique fingerprint.

Cite this