Analysis of complementarity among three sets of the features and their fusion for spatial steganography

doi:10.7523/j.issn.2095-6134.2012.2.018

Abstract

Abstract:

In view of spatial steganography, we discuss the complementarity among three sets of the features including statistical moments of wavelet characteristic functions, high-order statistics, and subtractive pixel adjacency matrix, and we use the mutual information criterion and boosting feature selection to fuse the features. Analytic and experimental results show that the complementarity does exist among the features and the fusion enhances accuracy of steganalysis.

Key words: feature selection, feature fusion, spatial steganography, steganalysis

CLC Number:

TP301

ZHANG Tao, ZHAO Xian-Feng, HUANG Wei, SHENG Ren-Nong. Analysis of complementarity among three sets of the features and their fusion for spatial steganography[J]. , 2012, (2): 264-270.

References

[1] Xuan G R, Shi Y Q, Gao J J, et al. Steganalysis based on multiple features formed by statistical moments of wavelet characteristic functions //Barni M. Proceedings of 2005 International Workshop on Information Hiding, LNCS 3727. Berlin: Springer-Verlag, 2005: 262-277.
[2] Lyu S, Farid H. Detecting hidden messages using higher-order statistics and support vector machine //Petitcolas F. Proceedings of 2002 International Workshop on Information Hiding, LNCS 2578. Berlin: Springer-Verlag, 2003: 340-354.
[3] Pevny T, Bas P, Fridrich J. Steganalysis by subtractive pixel adjacency matrix[J]. IEEE Transactions on Information Forensics and Security, 2010, 5(2): 215-224.
[4] Xuan G R, Shi Y Q, Huang C, et al. Steganalysis using high-dimensional features derived from co-occurrence matrix and class-wise non-principal components analysis (CNPCA) //Shi Y Q, Joen B. Proceedings of 2006 International Workshop on Digital Watermarking, LNCS 4832. Berlin: Springer-Verlag, 2006: 49-60.
[5] Pevny T, Fridrich J. Merging Markov and DCT features for multi-class JPEG steganalysis //Delp E, Wong P. Proceedings of Security, Steganography, and Watermarking of Multimedia Contents IX, SPIE 6505. Washington: SPIE Press, 2006: 650503/1-13.
[6] 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.
[7] Lin G S, Yeh C H, Kuo C J. Data hiding domain classification for blind image steganalysis //Lee D T. Proceedings of 2004 IEEE International Conference on Multimedia and Expo. 2004, 1(3): 907-910.
[8] Chiew K L, Pieprzyk J. Binary image steganographic classification based on multi-class Steganalysis //Kwak J. Proceedings of 2010 Information Security, Practice and Experience, LNCS 6047. Berlin: Springer-Verlag, 2010: 341-358.
[9] Jain A. Score normalization in multimodal biometric systems[J]. Pattern Recognition, 2005, 38(12): 2270-2285.
[10] Kharrazi M, Sencar H, Memon N. Improving steganalysis by fusion techniques: a case study with image steganography //Shi Y Q. LNCS Trans on Data Hiding and Multimedia Security, LNCS 4300. Berlin: Springer-Verlag, 2006: 123-137.
[11] Dong J, Chen X C, Guo L, et al. Fusion based blind image steganalysis by boosting feature selection //Shi Y. Proceedings of 2007 International Workshop on Digital Watermarking, LNCS 5041. Berlin: Springer-Verlag, 2008: 87-98.
[12] Sharp T. An implementation of key-based digital signal steganography //Moskowitz S. Proceedings of 2001 International Workshop on Information Hiding, LNCS 2137. Berlin: Springer-Verlag, 2001: 13-26.
[13] Fridrich J, Goljan M, Hogea D. Steganalysis of JPEG images: Breaking the F5 algorithm //Petitcolas F. Proceedings of 2002 International Workshop on Information Hiding, LNCS 2578. Berlin: Springer-Verlag, 2003: 310-323.
[14] Chen B, Wornell G. Quantization index modulation: a class of provably good methods for digital watermarking and information embedding[J]. IEEE Transactions on Information Theory, 2001, 47(4): 1423-1443.
[15] Escolano F, Suau P, Bonev B. Information theory in computer vision and pattern recognition[M]. Berlin: Springer-Verlag, 2009.
[16] Bas P, Furon T. BOWS-2.http://bows2.gipsa-lab.inpg.fr.
[17] Marvel L,Boncelet C,Retter C.Spread spectrum image steganography[J].IEEE Transaction on Image Processing,1999,8(8):1075-1083.
[18] Chang C, Lin C. LIBSVM 3.0. http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html.
[19] Langley P. Selection of relevant features in machine learning //Cun Y L. Proceedings of the AAAI Fall Symposium on Relevance. 1994: 140-144.