基于图像描述的文本信息隐藏

doi:10.13190/j.jbupt.2018-032

北京邮电大学学报 ›› 2018, Vol. 41 ›› Issue (6): 7-13.doi: 10.13190/j.jbupt.2018-032

基于图像描述的文本信息隐藏

薛一鸣¹, 周雪婧¹, 周小诗¹, 牛少彰², 文娟¹

1. 中国农业大学信息与电气工程学院, 北京 100083;
2. 北京邮电大学计算机学院, 北京 100876

收稿日期:2018-02-02 出版日期:2018-12-28 发布日期:2018-12-24
作者简介:薛一鸣(1968-),男,副教授;文娟(1982-),女,讲师,E-mail:wenjuan@cau.edu.cn.
基金资助:
国家自然科学基金项目（61802410，61872368）

Text Steganography Based on Image Caption

XUE Yi-ming¹, ZHOU Xue-jing¹, ZHOU Xiao-shi¹, NIU Shao-zhang², WEN Juan¹

1. College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China;
2. School of Computer Science, Beijing University of Posts and Telecommunication, Beijing 100876, China

Received:2018-02-02 Online:2018-12-28 Published:2018-12-24

摘要/Abstract

摘要： 针对文本信息隐藏嵌入容量低和语义连贯性差的问题，提出了一种基于神经网络图像描述的文本信息隐藏模型.将卷积神经网络与长短期记忆网络相结合，把图像特征和生成语句进行关联.从收发双方能否共享图像及模型参数的不同应用前提出发，设计了多种概率采样方式，从而生成载密的图像描述文本.实验结果表明，该算法具有较高的隐藏容量，载密描述句能较好地表达图像内容.该模型归属于"无载体"自然语言生成式信息隐藏，具有较好的隐蔽性和安全性.

关键词: 文本信息隐藏, 图像描述, 卷积神经网络, 长短期记忆网络

Abstract: Aiming at the problem of low embedding capacity and poor semantic coherence of text steganography, a text steganographic scheme based on neural image caption is proposed. An encode-decode structure with a combination of long short term memory and convolution neural network is used to model the joint probability distributions between image features and the descriptive sentences. Two methods with different sampling process are designed from the perspectives of sharing and non-sharing models. Experimental results show that the proposed model can achieve high embedding capacity and desirable text quality. This scheme belongs to "carrier-free" steganography and has good security.

Key words: text steganography, image caption, convolutional neural network, long short term memory

中图分类号:

TP309.2

薛一鸣, 周雪婧, 周小诗, 牛少彰, 文娟. 基于图像描述的文本信息隐藏[J]. 北京邮电大学学报, 2018, 41(6): 7-13.

XUE Yi-ming, ZHOU Xue-jing, ZHOU Xiao-shi, NIU Shao-zhang, WEN Juan. Text Steganography Based on Image Caption[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2018, 41(6): 7-13.

参考文献

[1] Fu Zhangjie, Sun Xingming, Shu Jiangang, et al. New forensic methods for ooxml format documents[J]. Lecture Notes in Computer Science, 2014(8389):503-513.
[2] Yajam H, Mousavi A. A new linguistic steganography scheme based on lexical substitution[C]//International Isc Conference on Information Security and Cryptology. Tehran:IEEE Press, 2014:155-160.
[3] Cao Qi, Sun Xingming, Xiang Lingyun. A secure text steganography based on synonym substitution[C]//IEEE Conference Anthology. China:IEEE Press, 2013:1-3.
[4] Topkara M, Topkara U, Atallah M J. Information hiding through errors:a confusing approach[J]. SPIE Procee-dings, 2007(6505):1-12.
[5] 戴祖旭, 洪帆, 崔国华. 基于词性标记串统计特性的文本数字水印算法[J]. 通信学报, 2007, 28(4):108-113. Dai Zuxu, Hong Fan, Cui Guohua. Watermarking text document based on statistic property of part of speech string[J]. Journal on Communications, 2007, 28(4):108-113.
[6] Jin C, Zhang D, Pan M. Chinese text information hiding based on paraphrasing technology[C]//International Conference of Information Science and Management Engineering. China:IEEE Press, 2010:39-42.
[7] Grothoff C, Grothoff K, Stutsman R. Translation-based steganography[J]. Journal of Computer Security, 2009, 17(3):269-303.
[8] Mckellar D. Spammimic[EB/OL]. 2017. http://www.spammimic.com.
[9] Chapman M, Davida G. Nicetext[EB/OL]. 2017. http://www.securityfocus.com/tools/1183.
[10] He J, Zhou M. Generating Chinese metrical poetry by a statistical MT approach[J]. Journal of Chinese Information Processing, 2010, 24(2):96-103.
[11] Luo Yubo, Huang Yongfeng, Chang Chinchen, 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.
[12] Kyunghyun C, Dzmitry B, Fethi B, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Conference on Empirical Methods in Natural Language Processing(EMNLP). Qatar:Association for Computational Linguistics, 2014:1724-1734.
[13] Sermanet P, Eigen D, LeCun Y, et al. Overfeat:integrated recognition, localization and detection using convolutional networks[C]//International Conference on Learning Representations. Banff:arXiv preprint, 2013:1312, 6229.
[14] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[15] Oriol V, Alexander T, Samy B, et al. Show and tell:a neural image caption generator[C]//Computer Vision and Pattern Recognition. Boston:IEEE press, 2015:3156-3164.
[16] Kelvin X, Jimmy L B, Ryan K, et al. Show, attend and tell:neural image caption generation with visual attention[C]//Proceeding of the 32^nd International Conference on Machine Learning. France:ACM press, 2015:2048-2057.
[17] Wu Q, Shen C S H, Liu L Q, et al. What value do explicit high level concepts have in vision to language problems[C]//Computer Vision and Pattern Recognition. Lasa Vegas:IEEE press, 2016:203-212.
[18] Andrei K, Li F F. Deep visual-semantic alignments for generating image descriptions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):664-676.
[19] Rashtchian C, Young P, Hodosh M, et al. Collecting image annotations using amazon's mechanical turk[C]//In NAACL HLT Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk. California:ACM press, 2010:139-147.
[20] Kishore P, Salim R, Todd W, et al. Bleu:a method for automatic evaluation of machine translation[C]//Proceedings of the 40^th Annual Meeting of the Association for Computational Linguistics. Philadelphia:ACM press, 2002:311-318.

基于图像描述的文本信息隐藏

Text Steganography Based on Image Caption

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]	彭维平王戈宋成阎俊豪. 面向高移动性车联网场景的预测卸载决策算法[J]. 北京邮电大学学报, 2023, 46(2): 43-49.
[2]	余佳润王亚峰. 一种低信噪比下基于深度学习的DoA估计方法[J]. 北京邮电大学学报, 2022, 45(6): 119-125.
[3]	刘金铭张玉艳张碧玲. 基于LSTM-KF的无人机航迹跟踪算法[J]. 北京邮电大学学报, 2022, 45(5): 121-128.
[4]	叶康张淑军郭淇李辉崔雪红. 基于CM-Transformer的连续手语识别[J]. 北京邮电大学学报, 2022, 45(5): 49-53,78.
[5]	武兴坤, 罗涛, 刘爱军, 杨明, 张文静. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[6]	武兴坤罗涛刘爱军杨明张文静李剑峰李文秀. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[7]	许同乐, 孟良, 孔晓佳, 苏元浩, 孙砚飞. 基于EEMD的ICNN故障诊断方法[J]. 北京邮电大学学报, 2022, 45(2): 110-116.
[8]	李晓辉, 王先文, 樊韬, 刘佳文, 万宏杰. 基于卷积神经网络的高性能5G下行同步算法[J]. 北京邮电大学学报, 2022, 45(2): 117-123.
[9]	王靖, 姜竹青, 门爱东, 郭晓强, 王智康. 阶梯式图像去噪方法[J]. 北京邮电大学学报, 2022, 45(1): 52-57.
[10]	刘永利, 朱亚孟, 晁浩. 多策略MRFO算法的卷积神经网络超参数优化[J]. 北京邮电大学学报, 2021, 44(6): 83-88,95.
[11]	普运伟, 郭江, 刘涛涛, 吴海潇. 基于多学习单元卷积神经网络的雷达辐射源信号识别[J]. 北京邮电大学学报, 2021, 44(6): 74-82.
[12]	王鑫炎, 王青山, 马晓迪, 刘鹏, 戴海鹏. 一种基于滑动窗口分割的中国手语识别系统[J]. 北京邮电大学学报, 2021, 44(5): 48-54.
[13]	王艺霏, 莫爽, 吴文睿, 范少华, 肖丁. 基于内外卷积网络的网络入侵检测[J]. 北京邮电大学学报, 2021, 44(5): 94-100.
[14]	刘国桢, 陈鸿龙. 卷积记忆图协同过滤[J]. 北京邮电大学学报, 2021, 44(3): 21-26.
[15]	彭鹏, 李卓, 梁纪峰, 马天祥, 刘开华. 支持泛洪攻击检测的命名数据网PIT[J]. 北京邮电大学学报, 2021, 44(2): 61-67.