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


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
Publication statusAccepted for publication - 21 Aug 2020
Event2020 IEEE International Conference on Systems, Man, and Cybernetics - Toronto, Canada
Duration: 11 Oct 202014 Oct 2020


Conference2020 IEEE International Conference on Systems, Man, and Cybernetics
Abbreviated titleSMC 2020
Internet address


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


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