DGANS:robustness image steganography model based on double GAN
Deep convolutional neural networks can be effectively applied to large-capacity image steganography,but the research on their robustness is rarely reported.The DGANS (double-GAN-based steganography) applies the deep learning framework in image steganography,which is optimized to resist small geometr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2020-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020019/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539337577037824 |
|---|---|
| author | Leqing ZHU Yu GUO Lingqiang MO Daxing ZHANG |
| author_facet | Leqing ZHU Yu GUO Lingqiang MO Daxing ZHANG |
| author_sort | Leqing ZHU |
| collection | DOAJ |
| description | Deep convolutional neural networks can be effectively applied to large-capacity image steganography,but the research on their robustness is rarely reported.The DGANS (double-GAN-based steganography) applies the deep learning framework in image steganography,which is optimized to resist small geometric distortions so as to improve the model’s robustness.DGANS is made up of two consecutive generative adversarial networks that can hide a grayscale image into another color or grayscale image of the same size and can restore it later.The generated stego-images are augmented and used to further train and strengthen the reveal network so as to make it adaptive to small geometric distortion of input images.Experimental results suggest that DGANS can not only realize high-capacity image steganography,but also can resist geometric attacks within certain range,which demonstrates better robustness than similar models. |
| format | Article |
| id | doaj-art-352b2894877e464bb94acdfdea1e1fee |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2020-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-352b2894877e464bb94acdfdea1e1fee2025-01-14T07:18:25ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2020-01-014112513359732701DGANS:robustness image steganography model based on double GANLeqing ZHUYu GUOLingqiang MODaxing ZHANGDeep convolutional neural networks can be effectively applied to large-capacity image steganography,but the research on their robustness is rarely reported.The DGANS (double-GAN-based steganography) applies the deep learning framework in image steganography,which is optimized to resist small geometric distortions so as to improve the model’s robustness.DGANS is made up of two consecutive generative adversarial networks that can hide a grayscale image into another color or grayscale image of the same size and can restore it later.The generated stego-images are augmented and used to further train and strengthen the reveal network so as to make it adaptive to small geometric distortion of input images.Experimental results suggest that DGANS can not only realize high-capacity image steganography,but also can resist geometric attacks within certain range,which demonstrates better robustness than similar models.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020019/image steganographyrobustnessdouble GANdeep learning |
| spellingShingle | Leqing ZHU Yu GUO Lingqiang MO Daxing ZHANG DGANS:robustness image steganography model based on double GAN Tongxin xuebao image steganography robustness double GAN deep learning |
| title | DGANS:robustness image steganography model based on double GAN |
| title_full | DGANS:robustness image steganography model based on double GAN |
| title_fullStr | DGANS:robustness image steganography model based on double GAN |
| title_full_unstemmed | DGANS:robustness image steganography model based on double GAN |
| title_short | DGANS:robustness image steganography model based on double GAN |
| title_sort | dgans robustness image steganography model based on double gan |
| topic | image steganography robustness double GAN deep learning |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020019/ |
| work_keys_str_mv | AT leqingzhu dgansrobustnessimagesteganographymodelbasedondoublegan AT yuguo dgansrobustnessimagesteganographymodelbasedondoublegan AT lingqiangmo dgansrobustnessimagesteganographymodelbasedondoublegan AT daxingzhang dgansrobustnessimagesteganographymodelbasedondoublegan |