DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data Hiding
Data hiding is the technique of embedding data into video or audio media. With the development of deep neural networks (DNN), the quality of images generated by novel data hiding methods based on DNN is getting better. However, there is still room for the similarity between the original images and t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/14/1/151 |
| _version_ | 1797490075496349696 |
|---|---|
| author | Xintao Duan Lei Li Yao Su Wenxin Wang En Zhang Xianfang Wang |
| author_facet | Xintao Duan Lei Li Yao Su Wenxin Wang En Zhang Xianfang Wang |
| author_sort | Xintao Duan |
| collection | DOAJ |
| description | Data hiding is the technique of embedding data into video or audio media. With the development of deep neural networks (DNN), the quality of images generated by novel data hiding methods based on DNN is getting better. However, there is still room for the similarity between the original images and the images generated by the DNN models which were trained based on the existing hiding frameworks to improve, and it is hard for the receiver to distinguish whether the container image is from the real sender. We propose a framework by introducing a key_img for using the over-fitting characteristic of DNN and combined with difference image grafting symmetrically, named difference image grafting deep hiding (DIGDH). The key_img can be used to identify whether the container image is from the real sender easily. The experimental results show that without changing the structures of networks, the models trained based on the proposed framework can generate images with higher similarity to original cover and secret images. According to the analysis results of the steganalysis tool named StegExpose, the container images generated by the hiding model trained based on the proposed framework is closer to the random distribution. |
| first_indexed | 2024-03-10T00:25:46Z |
| format | Article |
| id | doaj.art-7615ef426a5d4b87bcab802e11775872 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-10T00:25:46Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-7615ef426a5d4b87bcab802e117758722023-11-23T15:34:14ZengMDPI AGSymmetry2073-89942022-01-0114115110.3390/sym14010151DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data HidingXintao Duan0Lei Li1Yao Su2Wenxin Wang3En Zhang4Xianfang Wang5College of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, ChinaCollege of Computer Science and Technology, Henan Institute of Technology, Xinxiang 453003, ChinaData hiding is the technique of embedding data into video or audio media. With the development of deep neural networks (DNN), the quality of images generated by novel data hiding methods based on DNN is getting better. However, there is still room for the similarity between the original images and the images generated by the DNN models which were trained based on the existing hiding frameworks to improve, and it is hard for the receiver to distinguish whether the container image is from the real sender. We propose a framework by introducing a key_img for using the over-fitting characteristic of DNN and combined with difference image grafting symmetrically, named difference image grafting deep hiding (DIGDH). The key_img can be used to identify whether the container image is from the real sender easily. The experimental results show that without changing the structures of networks, the models trained based on the proposed framework can generate images with higher similarity to original cover and secret images. According to the analysis results of the steganalysis tool named StegExpose, the container images generated by the hiding model trained based on the proposed framework is closer to the random distribution.https://www.mdpi.com/2073-8994/14/1/151DIGDHimage hidingframework of image hidinghigh capacity data hiding |
| spellingShingle | Xintao Duan Lei Li Yao Su Wenxin Wang En Zhang Xianfang Wang DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data Hiding Symmetry DIGDH image hiding framework of image hiding high capacity data hiding |
| title | DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data Hiding |
| title_full | DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data Hiding |
| title_fullStr | DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data Hiding |
| title_full_unstemmed | DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data Hiding |
| title_short | DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data Hiding |
| title_sort | digdh a novel framework of difference image grafting deep hiding for image data hiding |
| topic | DIGDH image hiding framework of image hiding high capacity data hiding |
| url | https://www.mdpi.com/2073-8994/14/1/151 |
| work_keys_str_mv | AT xintaoduan digdhanovelframeworkofdifferenceimagegraftingdeephidingforimagedatahiding AT leili digdhanovelframeworkofdifferenceimagegraftingdeephidingforimagedatahiding AT yaosu digdhanovelframeworkofdifferenceimagegraftingdeephidingforimagedatahiding AT wenxinwang digdhanovelframeworkofdifferenceimagegraftingdeephidingforimagedatahiding AT enzhang digdhanovelframeworkofdifferenceimagegraftingdeephidingforimagedatahiding AT xianfangwang digdhanovelframeworkofdifferenceimagegraftingdeephidingforimagedatahiding |