High-Capacity Information Hiding Based on Residual Network

Abstract

To solve the problem of the low capacity of traditional information hiding and steganography, the deep neural network is used to construct a hidden network and a decoding network to hide one image into another. In this paper, the ResNet (Residual Network) has a good effect in feature extraction, and the residual block is used in the hidden network. First, the hidden network encoded the secret image into cover image. During the encoding process, the steganography image mimics the distribution of the cover image as much as possible. Then, the receiver sends the steganography image to the decoding network to obtain the secret image. Experimental results indicate that the scheme will solve the obvious problems of visual cues, also improve the ability of embedding.

Keywords:

• Information hiding
• image steganography
• deep neural network
• residual block
• ResNet

Additional information

Funding

This work supported by Key Scientific Research Projects of Colleges and Universities in Henan Province [grant numbers 19B510005, 20B413004].

Notes on contributors

Xintao Duan

Xintao Duan received the Ph.D. degree from Shanghai University, Shanghai, China, in 2011. He is currently an Associate Professor with the College of Computer and Information Engineering, Henan Normal University. His major research interests include image processing, deep learning, and information security. Corresponding author. Email: [email protected]

Baoxia Li

Baoxia Li received the B.S. degree from HeNan Normal University, China, in 2017. She is currently pursuing the M.S. degree with the College of Computer and Information Engineering, Henan Normal University. Her research interests include image processing, deep learning, and image steganography. Email: [email protected]

Zimei Xie

Zimei Xie received the M.S. degree from Shantou University, Shantou, China, in 2006. She is a lecturer in Henan Normal University Xinxiang, China. Her current research interests include areas of image processing and machine learning. Email: [email protected]

Dongli Yue

Dongli Yue received the M.S. degree from Chinese Academy of Sciences, Hefei, China in 2003. She is a associate professor in Henan Normal University, Xinxiang, China. Her current research interests include areas of image processing and machine learning. Email: [email protected]

Yuanyuan Ma

Yuanyuan Ma received the B.S. and M.S. degree from Henan Normal University, Xinxiang, China, in 2004 and 2007, respectively. She received the Ph.D. from Zhengzhou Information Science and Technology Institute, Zhengzhou, China, in 2019. She is a lecturer of Henan Normal University. Her research interest is image steganalysis technique. Email: [email protected]