Open Access

ARTICLE

High Visual Quality Image Steganography Based on Encoder-Decoder Model

Yan Wang^*, Zhangjie Fu, Xingming Sun
School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, China
* Corresponding Author: Yan Wang. Email:

Journal of Cyber Security 2020, 2(3), 115-121. https://doi.org/10.32604/jcs.2020.012275

Received 23 June 2020; Accepted 21 July 2020; Issue published 14 September 2020

Abstract

Nowadays, with the popularization of network technology, more and more people are concerned about the problem of cyber security. Steganography, a technique dedicated to protecting peoples’ private data, has become a hot topic in the research field. However, there are still some problems in the current research. For example, the visual quality of dense images generated by some steganographic algorithms is not good enough; the security of the steganographic algorithm is not high enough, which makes it easy to be attacked by others. In this paper, we propose a novel high visual quality image steganographic neural network based on encoder-decoder model to solve these problems mentioned above. Firstly, we design a novel encoder module by applying the structure of UNet++, which aims to achieve higher visual quality. Then, the steganalyzer is heuristically added into the model in order to improve the security. Finally, the network model is used to generate the stego images via adversarial training. Experimental results demonstrate that our proposed scheme can achieve better performance in terms of visual quality and security.

---

Keywords

Steganaography; visual quality; cyber security

---