DGANS:robustness image steganography model based on double GAN

Leqing ZHU; Yu GUO; Lingqiang MO; Daxing ZHANG

doi:10.11959/j.issn.1000-436x.2020019

您当前的位置：

首页 >

文章列表页 >

DGANS:robustness image steganography model based on double GAN

Papers | 更新时间：2024-06-05

- DGANS:robustness image steganography model based on double GAN
- Journal on Communications Vol. 41, Issue 1, Pages: 125-133(2020)
- 作者机构：
  
  1. 浙江工商大学计算机与信息工程学院，浙江杭州 310018
  2. 杭州电子科技大学计算机学院，浙江杭州 310018
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(61572160);The Natural Science Foundation of Zhejiang Province(LY20F020002)
- DOI：10.11959/j.issn.1000-436x.2020019
  CLC： TP391
- Online First：2020-01，
  
  Published：25 January 2020
- 稿件说明：
移动端阅览
Leqing ZHU, Yu GUO, Lingqiang MO, et al. DGANS:robustness image steganography model based on double GAN[J]. Journal on Communications, 2020, 41(1): 125-133.
DOI：

Leqing ZHU, Yu GUO, Lingqiang MO, et al. DGANS:robustness image steganography model based on double GAN[J]. Journal on Communications, 2020, 41(1): 125-133. DOI： 10.11959/j.issn.1000-436x.2020019.

摘要

深度卷积神经网络可有效地应用于大容量图像信息隐写，然而其稳健性研究却鲜有报道。双重生成式对抗网络（DGANS）模型对深度学习框架应用于图像隐写时，针对小幅度几何变换攻击进行了优化设计，从而提高模型的稳健性。DGANS由2个串联的生成式对抗网络构成，可将灰度图像隐藏到相同大小的彩色或灰度图像中并还原。通过对生成的含密图像进行数据增强并进一步强化训练提取网络，使提取网络对输入图像的几何变换具有适应性。实验结果表明，DGAN不仅可以实现高容量的图像信息隐写，而且可以对抗一定范围内的几何攻击，比同类模型有更好的稳健性。

Abstract

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.

关键词

Keywords

references

沈昌祥 , 张焕国 , 冯登国 , 等 . 信息安全综述 [J ] . 中国科学(信息科学) , 2007 , 37 ( 1 ): 129 - 150 .

SHEN C X , ZHANG H G , FENG D G , et al . Survey on information security [J ] . Science in China Series (Information Sciences) , 2007 , 37 ( 1 ): 129 - 150 .

王向阳 , 杨红颖 . DCT域自适应彩色图像二维数字水印算法研究 [J ] . 计算机辅助设计与图形学学报 , 2004 , 16 ( 2 ): 243 - 247 .

WANG X Y , YANG H Y . Adaptive 2-D color image watermarking based on DCT [J ] . Journal of Computer-Aided Design and Computer Graphics , 2004 , 16 ( 2 ): 243 - 247 .

王向阳 , 杨红颖 . 基于视觉掩蔽特性的小波域彩色数字水印技术 [J ] . 计算机辅助设计与图形学学报 , 2004 , 16 ( 9 ): 1240 - 1243 .

WANG X Y , YANG H Y . Color digital watermarking based on integer lifting wavelet transform and visual masking [J ] . Journal of Computer-Aided Design and Computer Graphics , 2004 , 16 ( 9 ): 1240 - 1243 .

PEVNÝ T , FILLER T , BAS P . Using high~dimensional image models to perform highly undetectable steganography [C ] // International Workshop on Information Hiding . Springer , 2010 : 161 - 177 .

HOLUB V , FRIDRICH J , DENEMARK T . Universal distortion function for steganography in an arbitrary domain [J ] . EURASIP Journal on Information Security , 2014 , 1 ( 1 ):1.

HOLUB V , FRIDRICH J . Designing steganographic distortion using directional filters [C ] // IEEE International Workshop on Information Forensics ＆ Security . IEEE , 2012 : 234 - 239 .

SHI H C , DONG J , WANG W , et al . SSGAN:secure steganography based on generative adversarial networks [C ] // 18th Pacific-Rim Conference on Multimedia . Springer , 2017 : 534 - 544 .

ARJOVSKY M , CHINTALA S , BOTTOU L . Wasserstein GAN [J ] . arXiv Preprint,arXiv:1701.07875 , 2017 : 1 - 32 .

HAYES J , DANEZIS G . Ste-GAN-ography:generating steganographic images via adversarial training [J ] . arXiv Preprint,arXiv:170300371v2 , 2017 : 1 - 9 .

REHMAN A U , RAHIM R , NADEEM S , et al . End-to-end trained CNN encode-decoder networks for image steganography [J ] . arXiv Preprint,arXiv:1711.07201 , 2017 : 1 - 5 .

BALUJA S , . Hiding images in plain sight:deep steganography [C ] // Advances in Neural Information Processing Systems . 2017 :

CHU C , ZHMOGINOV A , SANDLER M . CycleGAN,a master of steganography [C ] // Thirty-first Conference on Neural Information Processing Systems . 2017 : 1 - 6 .

TANG W , TAN S , LI B , et al . Automatic steganographic distortion learning using a generative adversarial network [J ] . IEEE Signal Processing Letters , 2017 , 24 ( 10 ): 1547 - 1551 .

ZHANG R , DONG S Q , LIU J Y . Invisible steganography via generative adversarial networks [J ] . Multimedia Tools and Applications , 2019 , 78 ( 7 ): 8559 - 8575 .

WU P , YANG Y , LI X . StegNet:MEGA image steganography capacity with deep convolutional network [J ] . Future Internet , 2018 , 10 ( 6 ): 54 - 68 .

DUAN X T , JIA K , LI B X , et al . Reversible image steganography scheme based on a U-Net structure [J ] . IEEE Access , 2019 , 7 ( 1 ): 9314 - 9323 .

XU G , . Deep convolutional neural network to detect J-UNIWARD [C ] // The 5th ACM Workshop on Information Hiding and Multimedia Security . 2017 : 67 - 73 .

SZEGEDY C , VANHOUCKE V , IOFFE S , et al . Rethinking the inception architecture for computer vision [C ] // IEEE Conference on Computer Vision and Pattern Recognition . 2016 : 2818 - 2826 .

IOFFE S , SZEGEDY C . Batch normalization:accelerating deep network training by reducing internal covariate shift [J ] . arXiv Preprint,arXiv:1502 ,03167,2015.

GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial nets [C ] // International Conference on Neural Information Processing Systems . 2014 : 2672 - 2680 .

WANG Z , BOVIK A , SHEIKH H R , et al . Image quality assessment:from error visibility to structural similarity [J ] . IEEE Transactions on Image Processing , 2004 , 13 ( 4 ): 600 - 612 .

EVERINGHAM M . The PASCAL visual object classes challenge(VOC2007)Results [J ] . Lecture Notes in Computer Science , 2007 , 111 ( 1 ): 98 - 136 .

YE J , NI J , YI Y . Deep learning hierarchical representations for image steganalysis [J ] . IEEE Transactions on Information Forensics and Security , 2017 , 12 ( 11 ): 2545 - 2557 .

Views

523

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

High-capacity image steganography algorithm combining image encryption and deep learning

Review of unsupervised anomaly detection techniques for medical imaging

Target visibility prediction method based on cost-sensitive CNN-BiLSTM network

Multi-modal semantics aided mmWave beam prediction method in industrial haze environment

Robust RF fingerprint identification under temporal domain shifts via confidence discrepancy and entropy minimization

Related Author

Xiaoyuan YANG

Xinliang BI

Jia LIU

Siyuan HUANG

Zhao Yingcheng

Song Xiaogang

Shi Zhenghao

You Zhenzhen

Related Institution

College of Cryptographic Engineering, Engineering University of PAP

Key Laboratory of Network and Information Security of the PAP

School of Computer Science and Engineering, Xi’an University of Technology

Shaanxi Key Laboratory for Network Computing and Security Technology

Human Machine Integration Intelligent Robot Shaanxi Provincial University Engineering Research Center

AI问答

⁰