北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2012, Vol. 35 ›› Issue (2): 99-103.doi: 10.13190/jbupt.201202.99.dongxz

• 研究报告 • 上一篇    下一篇

MB隐写分析算法

董秀则1,2,3,张茹1,3,钮心忻1   

  1. 1北京邮电大学 信息安全中心, 北京 100876; 2北京电子科技学院 电子信息工程系, 北京 100070; 3信息网络安全公安部重点实验室, 上海 201204
  • 收稿日期:2011-05-13 修回日期:2011-08-22 出版日期:2012-04-28 发布日期:2012-01-05
  • 通讯作者: 董秀则 E-mail:dongxz@besti.edu.cn
  • 作者简介:董秀则(1976-),男,讲师,博士生,E-mail:dongxz@besti.edu.cn 钮心忻(1963-),女,教授,博士生导师
  • 基金资助:

    国家自然科学基金项目(61003284,61170271);中央高校基本科研业务费专项资金项目(BUPT2009RC0126);信息网络安全公安部重点实验室开放基金资助课题

A Steganalysis Algorithm on MB Steganography

DONG Xiu-ze1,2,3,ZHANG Ru1,3,NIU Xin-xin1   

  1. 1Information Security Center, Beijing University of Posts and Telecommunications, Beijing 100876, China; 2Electronic and Information Engineering Department, Beijing Electronic Science and Technology Institute, Beijing 100070, China; 3Key Laboratory of Information Network Security, Ministry of Public Security, Shanghai 201204, China
  • Received:2011-05-13 Revised:2011-08-22 Online:2012-04-28 Published:2012-01-05
  • Contact: DONG XiuZe E-mail:dongxz@besti.edu.cn
  • Supported by:

    ;Fundamental Research Funds for the Central Universities under Grant

摘要:

对图像的高阶统计量进行研究,首先利用离散余弦变换(DCT)域共生矩阵、空域边界梯度能量和空域图像子块的虚特征值分解等对基于模型
(MB)隐写带来的变化进行描述,然后利用支持向量机(SVM)设计了MB隐写分析算法.实验结果表明,算法在保持低虚警率的同时具有较高的检出率.

关键词: MB隐写, 虚特征值分解, 支持向量机

Abstract:

A new steganalysis algorithm on model-based (MB) steganography is proposed after researching the high order statistics of images. The difference, imported by MB steganography is described by the co-occurrence discrete cosine transform(DCT) matrix, the boundary gradient energy in airspace and the imaginary eigenvalue decomposition. The MB steganography is detected using all of the features and support vector machine. Experiments show that this algorithm has a high accuracy rate of detection with a low false detection rate.

Key words: model-base steganography, imaginary eigenvalue decomposition, support vector machine

中图分类号: