.png){kind=icon}
.png){kind=icon}
Return
Hiding data hiding
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2022.12.008.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Data hiding (DH) is typically referred to as the art of hiding secret data into a given media for covert communication. In this paper, we make the first step towards hiding data hiding (HDH), which disguises DH tools, including a data embedding tool and a data extraction tool, as a deep neural network (DNN) with a normal task. In the method, after training a DNN for style transfer and DH from scratch, while the trained DNN can transfer the style of an image to the target style, it can also hide additional data into a cover image and extract data from a stego image. In other words, the DH tools are hidden by the DNN. Experimental results have shown the feasibility, applicability and superiority. (c) 2022 Elsevier B.V. All rights reserved.
Keywords:
Hiding data hiding
Covert communication
Deep learning
Security