基于神经机器翻译的文本隐写方法

doi:10.3969/j.issn.0255-8297.2020.06.014

应用科学学报 ›› 2020, Vol. 38 ›› Issue (6): 976-985.doi: 10.3969/j.issn.0255-8297.2020.06.014

• 信号与信息处理 • 上一篇

基于神经机器翻译的文本隐写方法

尉爽生¹, 杨忠良¹, 江旻宇², 黄永峰¹

1. 清华大学电子工程系, 北京 100084;
2. 莱斯大学计算机科学系, 美国得克萨斯州 77005

收稿日期:2019-11-29 发布日期:2020-12-08
通信作者: 黄永峰,教授,博导,研究方向为互联网及多媒体通信安全.E-mail:yfhuang@mail.tsinghua.edu.cn E-mail:yfhuang@mail.tsinghua.edu.cn
基金资助:
国家重点研发计划基金（No.SQ2018YGX210002）；国家自然科学基金（No.U1536201，No.U1636113，No.U1705261）资助

Text Steganography Based on Neural Machine Translation

YU Shuangsheng¹, YANG Zhongliang¹, JIANG Minyu², HUANG Yongfeng¹

1. Department of Electronic Engineering, Tsinghua University, Beijing 100084, China;
2. Department of Computer Science, Rice University, Texas 77005, United States

Received:2019-11-29 Published:2020-12-08

摘要/Abstract

摘要： 深度学习促进了自然语言处理技术的发展，基于文本生成的信息隐藏方法表现出了巨大的潜力.为此，提出了一种基于神经机器翻译的文本信息隐藏方法，在翻译文本生成过程中进行信息嵌入.神经机器翻译模型使用集束搜索（Beam Search）解码器，在翻译过程中通过Beam Search得到目标语言序列各位置上的候选单词集合，并将候选单词依据概率排序进行编码；然后在解码输出目标语言文本的过程中，根据秘密信息的二进制比特流选择对应编码的候选单词，实现以单词为单位的信息嵌入.实验结果表明，与已有的基于机器翻译的文本信息隐藏方法相比，该方法在隐藏容量方面明显提升，并且具有良好的抗隐写检测性和安全性.

关键词: 文本隐写, 信息隐藏, 神经网络, 机器翻译

Abstract: Deep learning has promoted the development of natural language processing technology, and the information hiding methods based on text generation show great potential in this area. This paper proposes a text information hiding method based on neural machine translation, which embeds information in the process of generating translated text. The neural machine translation model uses a Beam Search decoder, which is used to obtain the candidate words in the sentence sequence in the translation process, and to encode the candidate words according to the probability ranking. Then, in the process of decoding and outputting target language texts, corresponding encoded candidate words are selected according to the binary bitstream of secret information, so as to realize information embedding at word level. Experimental results show that compared with the existing text information hiding methods based on machine translation, this method significantly improves the rate of information embedding, and shows good capability and security in anti-steganography performance.

Key words: text steganography, information hiding, neural network, machine translation

中图分类号:

TP391.41

尉爽生, 杨忠良, 江旻宇, 黄永峰. 基于神经机器翻译的文本隐写方法[J]. 应用科学学报, 2020, 38(6): 976-985.

YU Shuangsheng, YANG Zhongliang, JIANG Minyu, HUANG Yongfeng. Text Steganography Based on Neural Machine Translation[J]. Journal of Applied Sciences, 2020, 38(6): 976-985.

参考文献

[1] Shannon C E. Communication theory of secrecy systems[J]. Bell System Technical Journal, 1949, 28(4):656-715.
[2] Bender W, Gruhl D, Morimoto N, et al. Techniques for data hiding[J]. IBM Systems Journal, 1996, 35(3):313-336.
[3] Brassil J T, Low S, Maxemchuk N F, et al. Marking text features of document images to deter illicit dissemination[J]//Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994, 3(2):315-319.
[4] Low S H, Maxemchuk N F, Brassil J, et al. Document marking and identification using both line and word shifting[C]//International Conference on Computer Communications, Boston, MA, USA, 1995:853-860.
[5] Bergmair R. Towards linguistic steganography:a systematic investigation of approaches, systems, and issues[J]. Derby:The University of Derby, 2004.
[6] Atallah M J, Mcdonough C J, Raskin V, et al. Natural language processing for information assurance and security:an overview and implementations[C]//Proceedings of the 2000 Workshop on New Security Paradigms, County Cork, Ireland, 2001:51-65.
[7] Dai W, Yu Y, Dai Y, et al. Text steganography system using Markov chain source model and DES algorithm[J]. Journal of Software, 2010, 5(7):785-792.
[8] Luo Y, Huang Y, Li F, et al. Text steganography based on Ci-poetry generation using Markov chain model[J]. KSⅡ Transactions on Internet and Information Systems, 2016, 10(9):4568-4584.
[9] Luo Y, Huang Y. Text steganography with high embedding rate:using recurrent neural networks to generate chinese classic poetry[C]//Proceedings of the 5th ACM workshop on information hiding and multimedia security. 2017:99-104.
[10] Fang T, Jaggi M, Argyraki K. Generating steganographic text with LSTMs[DB/OL]. arXiv preprint arXiv:1705.10742, 2017. DOI:10.18653/v1/P17-3017
[11] Yang Z L, Guo X Q, Chen Z M, et al. RNN-STEGA:linguistic steganography based on recurrent neural networks[J]. IEEE Transactions on Information Forensics and Security, 2018, 14(5):1280-1295.
[12] Grothoff C, Grothoff K, Alkhutova L, et al. Translation-based steganography[C]//International Workshop on Information Hiding. Heidelberg, Berlin:Springer, 2005:219-233.
[13] Stutsman R, Grothoff C, Atallah M, et al. Lost in just the translation[C]//Proceedings of the 2006 ACM symposium on Applied computing, Dijon, France, 2006:338-345.
[14] Meng P, Shi Y Q, Huang L, et al. LinL:Lost in n-best list[C]//International Workshop on Information Hiding. Heidelberg, Berlin:Springer, 2011:329-341.
[15] Sutskever I, Vinyals O, Le Q V, et al. Sequence to sequence learning with neural networks[J]. arXiv:Computation and Language, 2014.
[16] Bahdanau D, Cho K, Bengio Y, et al. Neural machine translation by jointly learning to align and translate[J]. arXiv:Computation and Language, 2014.
[17] Koehn P, Knowles R. Six challenges for neural machine translation[C]//Meeting of the Association for Computational Linguistics, Vancouver, Canada 2017:28-39.
[18] Press O, Smith N A. You maynot need attention[J]. arXiv preprint arXiv:1810.13409, 2018.
[19] Dyer C, Chahuneau V, Smith N A, et al. A simple, fast, and effective reparameterization of IBM model 2[C]//North American Chapter of the Association for Computational Linguistics, Atlanta, Georgia, USA 2013:644-648.
[20] Papineni K, Roukos S, Ward T, et al. Bleu:a method for automatic evaluation of machine translation[C]//Meeting of the Association for Computational Linguistics, Philadelphia, USA 2002:311-318.
[21] 孟朋. 自然语言信息隐藏与检测研究[D]. 合肥:中国科学技术大学, 2012.
[22] Chen Z, Huang L, Meng P, et al. Blind linguistic steganalysis against translation-based steganography[C]//International Workshop on Digital Watermarking, Berlin, Heidelberg:Springer, 2010:251-265.
[23] Yang Z, Huang Y, Zhang Y J. A fast and efficient text steganalysis method[J]. IEEE Signal Processing Letters, 2019, 26(4):627-631.

基于神经机器翻译的文本隐写方法

Text Steganography Based on Neural Machine Translation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	马飞虎, 金依辰, 孙翠羽. 基于EMD优化NAR动态神经网络的地铁客流量短时预测模型[J]. 应用科学学报, 2020, 38(6): 936-943.
[2]	王孟轩, 张胜, 王月, 雷霆, 杜渂. 改进的CRNN模型在警情文本分类中的研究与应用[J]. 应用科学学报, 2020, 38(3): 388-400.
[3]	孙容海, 施林甫, 俞春强, 劳欢, 唐振军. 面向密文图像信息隐藏的随机插值方法[J]. 应用科学学报, 2020, 38(3): 419-430.
[4]	司广文, 秦川, 姚恒, 韩彦芳, 张志超. 基于纹理特征分类与合成的鲁棒无载体信息隐藏[J]. 应用科学学报, 2020, 38(3): 441-454.
[5]	马鑫, 吴云, 鹿泽光. 基于混合神经网络的协同过滤推荐模型[J]. 应用科学学报, 2020, 38(3): 478-487.
[6]	刘伟, 章琬苓, 项世军. 基于LBP-MDCT和CNN的人脸活体检测算法[J]. 应用科学学报, 2019, 37(5): 609-617.
[7]	王灿军, 廖鑫, 陈嘉欣, 秦拯, 刘绪崇. 基于卷积神经网络的面部图像修饰检测[J]. 应用科学学报, 2019, 37(5): 618-630.
[8]	屈凌峰, 陈帆, 和红杰, 袁源. 基于位平面-块置乱的图像加密算法安全性分析[J]. 应用科学学报, 2019, 37(5): 631-642.
[9]	吴韵清, 吴鹏, 陈北京, 鞠兴旺, 高野. 基于残差全卷积网络的图像拼接定位算法[J]. 应用科学学报, 2019, 37(5): 651-662.
[10]	李松斌, 杨洁, 刘鹏, 王凌睿. 基于关联网络模型的H.264/AVC运动矢量调制信息隐藏检测方法[J]. 应用科学学报, 2019, 37(5): 663-672.
[11]	朱翌明, 陈帆, 和红杰, 陈鸿佑. 基于秘密信息驱动的正交GAN信息隐藏模型[J]. 应用科学学报, 2019, 37(5): 721-732.
[12]	王俊祥, 毛宁雄, 赵怡, 王春桃. 面向全容量的高性能彩色图像可逆信息隐藏算法[J]. 应用科学学报, 2019, 37(5): 744-760.
[13]	魏巍, 全海燕. 基于单形进化的径向基网络训练算法[J]. 应用科学学报, 2019, 37(4): 459-468.
[14]	靳华中, 刘潇龙, 胡梓珂. 一种结合全局和局部特征的图像描述生成模型[J]. 应用科学学报, 2019, 37(4): 501-509.
[15]	赵云山, 段友祥. 基于Attention机制的卷积神经网络文本分类模型[J]. 应用科学学报, 2019, 37(4): 541-550.