作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (8): 141-143. doi: 10.3969/j.issn.1000-3428.2008.08.049

• 安全技术 • 上一篇    下一篇

基于统计特征和SVM的JPEG图像掩密分析

贵 琦1,柏 森1,2,孙 静1   

  1. (1. 重庆通信学院图像通信实验室,重庆 400035;2. 重庆大学计算机学院,重庆 400044)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-04-20 发布日期:2008-04-20

JPEG Images Steganalysis Based on Statistic Characteristic and SVM

GUI Qi1, BAI Sen1,2, SUN Jing1   

  1. (1. Image Communication Lab, Chongqing Communication Institute, Chongqing 400035;2. College of Computer Science, Chongqing University, Chongqing 400044)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-04-20 Published:2008-04-20

摘要: 提出一种能够有效检测含密JPEG图像的掩密分析方法,利用图像的一阶和二阶统计特征分别提取原始图像和掩密图像的直方图特征以及图像块内和块间的部分统计特征,采用支持向量机对原始图像和掩密图像的特征进行训练、分类并建立模型,达到通用检测的目的。实验结果表明,该算法能够对Jsteg, F5, OutGuess和MB等掩密算法进行有效分析。

关键词: 掩密术, 掩密分析, 统计特征, 支持向量机

Abstract: This paper presents a steganalysis scheme which can effectively attack JPEG steganographic. The method exploits the first and the second order statistic characteristics. It extracts these characteristics of histogram and the partial statistical characteristics of intra-block and inter-block from the cover-images and the stego-images respectively. In order to achieve the purpose of general detection, it uses Support Vector Machine(SVM) to train and distinguish these characteristics, and establishs the model. Experimental results show that the method performs well in steganalysis methods such as Jsteg, F5, OutGuess, and MB.

Key words: steganography, steganalysis, statistic characteristic, Support Vector Machine(SVM)

中图分类号: