Please wait a minute...
J4  2011, Vol. 45 Issue (9): 1528-1538    DOI: 10.3785/j.issn.1008-973X.2011.09.004
计算机技术﹑电信技术     
基于多域特征的JPEG图像盲检测算法
李卓,陈健,蒋晓宁,曾宪庭,潘雪增
浙江大学 计算机科学与技术学院,浙江 杭州 310027
Blind JPEG steganalysis based on multi-domain features
LI Zhuo, CHEN Jian, JIANG Xiao-ning, ZENG Xian-ting, PAN Xue-zeng
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
 全文: PDF  HTML
摘要:

为了提高图像信息隐藏盲检测的检测率,实现了一种从多个域提取统计特征的JPEG图像通用隐写分析算法.采用联合概率密度来计算离散余弦变换(DCT)系数间的相关性,将其扩展到小波域和空域,提取特征值;并使用同样的方法提取校准图像的特征值.二者的差值组成最终的特征向量训练分类器.对5种典型的JPEG隐写术,使用3种不同图像库进行了一系列的实验,结果表明:在嵌入率只有0.05 bpnc时,该算法检测率大于72%,与目前几种典型的通用隐写分析算法相比,具有更好的检测效果;特征约简能弱化高维特征向量间的相关性,提高分类精确度并大大节约分类时间,是通用隐写分析系统框架中一个重要的步骤.

Abstract:

A blind steganalysis method based on multi-domain features was proposed for JPEG images to improve the detection accuracy of blind detection scheme for image steganography. The joint probability density matrix was used to capture the correlations of neighboring coefficients in discrete cosine transform (DCT), and those in discrete wavelet transform (DWT) and spatial domain as the original features. In the same way, the calibrated features were extracted from the calibrated image. The differences between the original and calibrated features were considered to be the exact features used for training classifiers.Experiments were done for five kinds of typical JPEG steganography schemes in three different image libraries. Results validated that the detection accuracy of the proposed scheme was greater than 72% when the embedded ratio was only 0.05 bpnc. Compared with some classical blind steganalysis schemes, the proposed method provided higher detection accuracy. Experimental results demonstrate that the feature reduction is an important step in the blind detection framework, which can decrease the correlations of features of high dimensions, improve the detection accuracy and reduce the time of classification greatly.

出版日期: 2011-09-01
:  TP 309  
基金资助:

浙江省重大科技专项资助项目(2007C11088);浙江省科技计划资助项目(2008C21077).

通讯作者: 潘雪增,男,教授,博导.     E-mail: xzpan@zju.edu.cn
作者简介: 李卓(1984-),男,博士生,从事计算机安全、信息隐藏和隐写分析方面的研究.E-mail: lizhuo84@gmail.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  

引用本文:

李卓,陈健,蒋晓宁,曾宪庭,潘雪增. 基于多域特征的JPEG图像盲检测算法[J]. J4, 2011, 45(9): 1528-1538.

LI Zhuo, CHEN Jian, JIANG Xiao-ning, ZENG Xian-ting, PAN Xue-zeng. Blind JPEG steganalysis based on multi-domain features. J4, 2011, 45(9): 1528-1538.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2011.09.004        https://www.zjujournals.com/eng/CN/Y2011/V45/I9/1528

[1] 张涛, 平西建, 徐长勇. 基于图像平滑度的空域LSB嵌入的检测算法[J]. 计算机辅助设计与图形学学报, 2006, 18(10):1607-1612.
ZHANG Tao, PING Xijian, XU Changyong. Detection algorithm for spatial LSB embedding based on image smoothness[J]. Journal of Computer Aided Design & Computer Graphics, 2006, 18(10):1607-1612.
[2] GUI G, DIRIK A E, AVCIBAS I. Steganalytic features for JPEG compressionbased perturbed quantization[J]. IEEE Signal Processing Letters, 2007, 14(3):205-208.
[3] AVCIBAS I, MEMON N, SANKUR B. Steganalysis based on image quality metrics [C]∥ IEEE Fourth Workshop on Multimedia Signal Processing. Cannes, France: Institute of Electrical and Electronics Engineers Inc., 2001:517-522.
[4] FARID H, SIWEI L. Detecting hidden messages using higherorder statistics and support vector machines [C]∥ Proceedings of the 5th Information Hiding Workshop. Noordwijkerhout, Netherlands: Springer~Verlag, 2002: 340-354.
[5] FRIDRICH J. Featurebased steganalysis for JPEG images and its implications for future design of steganographic schemes [C]∥ Proceedings of the 6th Information Hiding Workshop. Toronto, Ontario, Canada: Springer~Verlag, 2005: 67-81.
[6] HARMSEN J, PEARLMAN W. Steganalysis of additive noise modelable information hiding [C]∥ Proceedings of SPIE Security Watermarking Multimedia Contents. Santa Clara, CA: SPIE, 2003: 131-142.
[7] SHI Y Q, XUAN G R, ZOU D K, et al. Steganalysis based on moments of characteristic functions using wavelet decomposition, predictionerror image, and neural network [C]∥ Proceedings of the IEEE International Conference on Multimedia & Expo 2005. Amsterdam, Netherlands:\
[s.n.\], 2005:269-272.
[8] SHI Y Q, CHEN C H, CHEN W. A Markov process based approach to effective attacking JPEG steganography [C]∥ Proceedings of the 8th Information Hiding Workshop. Alexandria, VA, USA: Springer~Verlag, 2007: 249-264.
[9] PENVY T, FRIDRICH J. Merging markov and DCT features for multiclass JPEG steganalysis [C]∥ Proceedings of SPIE Electronic Imaging, Security, Steganography, and Watermarking of Multimedia Contents IX. San Jose: Society for Imaging Science and Technology and SPIE. 2007, 650530-1-650530-13.
[10] CHEN C H, SHI Y Q. JPEG image steganalysis utilizing both intrablock and interblock correlations [C]∥ IEEE International Symposium on Circuits and Systems. Seattle, Washington, USA: IEEE, 2008: 3029-3032.
[11] 毛家发,林家骏,戴蒙. 基于图像攻击的隐藏信息盲检测技术[J]. 计算机学报, 2009, 32(2):318-327.
MAO Jiafa, LIN Jiajun, DAI Meng. An attacked image based hidden messages blind detect technique[J]. Chinese Journal of Computers, 2009, 32(2):318-327.
[12] LIU Q Z, SUNG A H, QIAO M Y. Improved detection and evaluation for JPEG steganalysis [C]∥ Proceedings of the Seventeen ACM International Conference on Multimedia, New York:\
[s.n.\], 2009:873-876.
[13] 黄方军,黄继武. 基于图像校准的通用型JPEG隐写分析[J]. 中国科学 F辑:信息科学, 2009, 39(4):383-390.
HUANG Fanjun, HUANG Jiwu. Calibration based universal JPEG steganalysis[J]. Science in China Series F: Information Sciences, 2009, 39(4):383-390.
[14] LUO X Y, WANG D S, HU W, et al. Blind detection for image steganography: a system framework and implementation[J]. International Journal of Innovative Computing, Information and Control, 2009, 5(2):433-442.
[15] LIE W N, LIN G S. A featurebased classification technique for blind image steganalysis[J]. IEEE Transactions on Multimedia, 2005, 7(6): 1007-1020.
[16] HOLOTYAK T, FRIDRICH J, VOLOSHYNOVSKIY S. Blind statistical steganalysis of additive steganography using wavelet higher order statistics [C]∥ Proceeds of the IFIP Conference on Communications and Multimedia Security. Salzburg,Austria:Springer LNCS, 2005,3677: 273-274.
[17] 平姈娣,刘祖根,史烈,等. 基于易变特征实现隐藏信息的盲检测[J]. 浙江大学学报:工学版, 2007, 41(3):374-379.
PING Lingdi, LIU Zugen, SHI Lie, et al. Variable characteristics based blind detection of hidden information [J]. Journal on Zhejiang University :E

[1] 王友卫, 刘元宁, 朱晓冬. 用于图像内容认证的半脆弱水印新算法[J]. J4, 2013, 47(6): 969-976.
[2] 姜励, 陈健, 平玲娣, 陈小平. 多线程程序的信息抹除和降密安全策略[J]. J4, 2010, 44(5): 854-862.
[3] 彭志宇, 李善平, 杨朝晖, 林欣. 信任管理中的匿名授权方法[J]. J4, 2010, 44(5): 897-902.
[4] 黄勇, 陈小平, 陈文智, 等. 支持动态调节的保密性和完整性统一模型[J]. J4, 2009, 43(8): 1377-1382.