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

This document is currently not available here.

Share

COinS