IDGAN: Information-Driven Generative Adversarial Network of Coverless Image Steganography
Traditional image steganography techniques complete the steganography process by embedding secret information into cover images, but steganalysis tools can easily detect detectable pixel changes that lead to the leakage of confidential information. The use of a generative adversarial network (GAN) m...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/13/2881 |
| _version_ | 1797591817777053696 |
|---|---|
| author | Chunying Zhang Xinkai Gao Xiaoxiao Liu Wei Hou Guanghui Yang Tao Xue Liya Wang Lu Liu |
| author_facet | Chunying Zhang Xinkai Gao Xiaoxiao Liu Wei Hou Guanghui Yang Tao Xue Liya Wang Lu Liu |
| author_sort | Chunying Zhang |
| collection | DOAJ |
| description | Traditional image steganography techniques complete the steganography process by embedding secret information into cover images, but steganalysis tools can easily detect detectable pixel changes that lead to the leakage of confidential information. The use of a generative adversarial network (GAN) makes it possible to embed information using a combination of information and noise in generating images to achieve steganography. However, this approach is usually accompanied by issues such as poor image quality and low steganography capacity. To address these challenges, we propose a steganography model based on a novel information-driven generative adversarial network (IDGAN), which fuses a GAN, attention mechanisms, and image interpolation techniques. We introduced an attention mechanism on top of the original GAN model to improve image accuracy. In the generation model, we replaced some transposed convolution operations with image interpolation for better quality of dense images. In contrast to traditional steganographic methods, the IDGAN generates images containing confidential information without using cover images and utilizes GANs for information embedding, thus having better anti-detection capability. Moreover, the IDGAN uses an attention mechanism to improve the image details and clarity and optimizes the steganography effect through an image interpolation algorithm. Experimental results demonstrate that the IDGAN achieves an accuracy of 99.4%, 95.4%, 93.2%, and 100% on the MNIST, Intel Image Classification, Flowers, and Face datasets, respectively, with an embedding rate of 0.17 bpp. The model effectively protects confidential information while maintaining high image quality. |
| first_indexed | 2024-03-11T01:42:46Z |
| format | Article |
| id | doaj.art-2dba598c77394997ba54704514f72fcf |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T01:42:46Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-2dba598c77394997ba54704514f72fcf2023-11-18T16:24:48ZengMDPI AGElectronics2079-92922023-06-011213288110.3390/electronics12132881IDGAN: Information-Driven Generative Adversarial Network of Coverless Image SteganographyChunying Zhang0Xinkai Gao1Xiaoxiao Liu2Wei Hou3Guanghui Yang4Tao Xue5Liya Wang6Lu Liu7College of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaHebei Key Laboratory of Data Science and Application, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaTraditional image steganography techniques complete the steganography process by embedding secret information into cover images, but steganalysis tools can easily detect detectable pixel changes that lead to the leakage of confidential information. The use of a generative adversarial network (GAN) makes it possible to embed information using a combination of information and noise in generating images to achieve steganography. However, this approach is usually accompanied by issues such as poor image quality and low steganography capacity. To address these challenges, we propose a steganography model based on a novel information-driven generative adversarial network (IDGAN), which fuses a GAN, attention mechanisms, and image interpolation techniques. We introduced an attention mechanism on top of the original GAN model to improve image accuracy. In the generation model, we replaced some transposed convolution operations with image interpolation for better quality of dense images. In contrast to traditional steganographic methods, the IDGAN generates images containing confidential information without using cover images and utilizes GANs for information embedding, thus having better anti-detection capability. Moreover, the IDGAN uses an attention mechanism to improve the image details and clarity and optimizes the steganography effect through an image interpolation algorithm. Experimental results demonstrate that the IDGAN achieves an accuracy of 99.4%, 95.4%, 93.2%, and 100% on the MNIST, Intel Image Classification, Flowers, and Face datasets, respectively, with an embedding rate of 0.17 bpp. The model effectively protects confidential information while maintaining high image quality.https://www.mdpi.com/2079-9292/12/13/2881coverless steganographygenerative adversarial networkattention mechanismsimage interpolationdense convolutional network |
| spellingShingle | Chunying Zhang Xinkai Gao Xiaoxiao Liu Wei Hou Guanghui Yang Tao Xue Liya Wang Lu Liu IDGAN: Information-Driven Generative Adversarial Network of Coverless Image Steganography Electronics coverless steganography generative adversarial network attention mechanisms image interpolation dense convolutional network |
| title | IDGAN: Information-Driven Generative Adversarial Network of Coverless Image Steganography |
| title_full | IDGAN: Information-Driven Generative Adversarial Network of Coverless Image Steganography |
| title_fullStr | IDGAN: Information-Driven Generative Adversarial Network of Coverless Image Steganography |
| title_full_unstemmed | IDGAN: Information-Driven Generative Adversarial Network of Coverless Image Steganography |
| title_short | IDGAN: Information-Driven Generative Adversarial Network of Coverless Image Steganography |
| title_sort | idgan information driven generative adversarial network of coverless image steganography |
| topic | coverless steganography generative adversarial network attention mechanisms image interpolation dense convolutional network |
| url | https://www.mdpi.com/2079-9292/12/13/2881 |
| work_keys_str_mv | AT chunyingzhang idganinformationdrivengenerativeadversarialnetworkofcoverlessimagesteganography AT xinkaigao idganinformationdrivengenerativeadversarialnetworkofcoverlessimagesteganography AT xiaoxiaoliu idganinformationdrivengenerativeadversarialnetworkofcoverlessimagesteganography AT weihou idganinformationdrivengenerativeadversarialnetworkofcoverlessimagesteganography AT guanghuiyang idganinformationdrivengenerativeadversarialnetworkofcoverlessimagesteganography AT taoxue idganinformationdrivengenerativeadversarialnetworkofcoverlessimagesteganography AT liyawang idganinformationdrivengenerativeadversarialnetworkofcoverlessimagesteganography AT luliu idganinformationdrivengenerativeadversarialnetworkofcoverlessimagesteganography |