基于GAN图像生成的信息隐藏技术综述

信息安全研究 ›› 2019, Vol. 5 ›› Issue (9): 771-777.

基于GAN图像生成的信息隐藏技术综述

周琳娜,吕欣一

国际关系学院信息科技学院

收稿日期:2019-09-06 出版日期:2019-09-15 发布日期:2019-09-06
通讯作者: 吕欣一
作者简介:周琳娜教授，主要研究方向为大数据行为分析、信息隐藏、多媒体内容取证。 Zhoulinna@tsinghua.edu.cn 吕欣一硕士研究生，主要研究方向为信息隐藏，信息安全。 lvxinyi_uir@163.com

The Review of Information Hiding Technology Based on GAN Image Generation

Received:2019-09-06 Online:2019-09-15 Published:2019-09-06

摘要/Abstract

摘要： 传统的隐写方式面临的威胁越来越大，隐写分析技术也逐渐成熟，针对这一问题，将生成式对抗网络引入隐写术中，可以减少载体修改痕迹，提高隐写的隐蔽性.介绍了生成式对抗网络的基本结构，总结了基于GAN图像生成的隐写技术的研究成果，并进行比较和分类.根据已有的技术手段提出了当前生成式对抗网络在隐写技术发展中的不足，对未来的研究方向进行了展望.

关键词: 生成式对抗网络, 信息隐藏, 隐写术, 深度学习, 图像生成

Abstract: The traditional steganography is facing more and more threats, and the steganographic analysis technology is gradually mature. To solve this problem, the Generative Adversarial Networks is introduced into the steganography, which can reduce the traces of carrier modification and improve the concealment of steganography. This paper introduces the basic structure of the Generative Adversarial Networks, summarizes, compares and classifies the research results of the steganography based on GAN image generation. According to the existing technical means, the shortcomings of the current Generative Adversarial Networks in the development of steganography are proposed, and the future research directions are prospected.

Key words: generative adversarial networks, information hiding, steganography, deep learning, image generation

周琳娜吕欣一. 基于GAN图像生成的信息隐藏技术综述[J]. 信息安全研究, 2019, 5(9): 771-777.

参考文献

[1]Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[OL].(2014-06-11)[2019-4-28].http://arxiv.org/abs/1406.2661 [2]Mirza M, Osindero S. Conditional Generative Adversarial Nets[OL]. (2014-11-6)[2019-4-28] https://arxiv.org/abs/1411.1784 [3]Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]// the Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe: ACM, 2017: 84-90 [4]Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[OL].(2015-11-9)[2019-4-28]. https://arxiv.org/abs/1511.06434 [5]Ledig C, Theis L, Huszar F, et al. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI: IEEE,2017:105-114 [6]Arjovsky M, Chintala S, Bottou L. Wasserstein GAN[OL].(2017-1-26)[2019-4-28] https://arxiv.org/abs/1701.07875 [7] Zhao Zhaoyu, Pan Yingwei, Ting Yao et al. Deep Semantic Hashing with Generative Adversarial Networks[C]//SIGIR'17 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2017:225-234 [8]Wang Weiyue, Huang Qiangui, You Suya, et al. Shape Inpainting Using 3D Generative Adversarial Network and Recurrent Convolutional Networks[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2317-2325 [9]Abadi Martín, Andersen D G. Learning to protect communications with adversarial neural cryptography [OL].(2016-10-21)[2019-4-28] https://arxiv.org/abs/1610.069 18 [10]刘佳,柯彦,雷雨,李军,刘明明,杨晓元,张敏情.生成对抗网络在图像隐写中的应用[J].武汉大学学报(理学版),2019,65(02):139-152 [11] Volkhonskiy D, Nazarov I, Borisenko B, et al. Steganographic Generative Adversarial Networks[OL]. (2017-5-16)[2019-5-1] https://arxiv.org/abs/1703.05502 [12] Shi Haichao, Dong Jing, Wang Wei, et al. SSGAN: Secure Steganography Based on Generative Adversarial Networks[G]//LNCS 10735: Pacific Rim Conference on Multimedia. Berlin: Springer, 2018:534-544 [13]Qian Yinlong, Dong Jing, Wang Wei, et al. Deep learning for steganalysis via convolutional neural networks[C]//Proceedings of SPIE - The International Society for Optical Engineering, San Francisco: SPIE, 2015:1-10 [14]王耀杰,钮可,杨晓元.基于生成对抗网络的信息隐藏方案[J].计算机应用, 2018,38(10): 2923-2928 [15]周志立,曹燚,孙星明. 基于图像Bag-of-Words模型的无载体信息隐藏[J]. 应用科学学报, 2016, 34(05): 527-536 [16]Chu C, Zhmoginov A, Sandler M, CycleGAN, a Master of Steganography[OL].(2017- 12-8)[2019-5-1] https://arxiv.org/abs/1712.02950 [17] Zhu Junyan, Park T , Isola P , et al. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [C]//Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks, Venice: IEEE, 2017: 2242-2251 [18] Odena A, Olah C, Shlens J. Conditional Image Synthesis With Auxiliary Classifier GANs[C]//International Conference on Machine Learning, Sydney: ICML,2017: 2642-2651. [19] 刘明明,张敏情,刘佳,高培贤,张英男.基于生成对抗网络的无载体信息隐藏[J].应用科学学报, 2018,36(02):371-382 [20]宋好娴. 基于生成模型的无载体信息隐藏[D].河南：河南师范大学, 2018 [21]Tan S, Li B. Stacked convolutional auto-encoders for steganalysis of digital images[C]//Signal and Information Processing Association Annual Summit and Conference, Siem Reap:APSIPA,2014: 1-4 [22]高培贤,魏立线,刘佳,刘明明.基于密集连接网络的图像隐写分析[J].计算机工程与应用,2018,54(15):74-77+146