An Embedding Cost Learning Framework Using GAN
Document Type
Article
Publication Date
1-1-2020
Abstract
Successful adaptive steganography has mainly focused on embedding the payload while minimizing an appropriately defined distortion function. The application of deep learning to steganalysis has greatly challenged present adaptive steganographic methods, but has also shown the potential for the improvement of steganography. This paper proposes a distortion function generating a framework for steganography. It has three modules: a generator with a U-Net architecture to translate a cover image into an embedding change probability map, a no-pre-training-required double-tanh function to approximate the optimal embedding simulator while preserving gradient norm during backpropagation in the adversarial training, and an enhanced steganalyzer based on a convolution neural network together with multiple high pass filters as the discriminator. Extensive experimental results on different datasets have shown that the proposed framework outperforms the current state-of-the-art steganographic schemes. Moreover, the adversarial training time is reduced dramatically compared with the GAN-based automatic steganographic distortion learning framework (ASDL-GAN).
Identifier
85073623719 (Scopus)
Publication Title
IEEE Transactions on Information Forensics and Security
External Full Text Location
https://doi.org/10.1109/TIFS.2019.2922229
e-ISSN
15566021
ISSN
15566013
First Page
839
Last Page
851
Volume
15
Grant
61772571
Fund Ref
National Natural Science Foundation of China
Recommended Citation
Yang, Jianhua; Ruan, Danyang; Huang, Jiwu; Kang, Xiangui; and Shi, Yun Qing, "An Embedding Cost Learning Framework Using GAN" (2020). Faculty Publications. 5752.
https://digitalcommons.njit.edu/fac_pubs/5752