Steganalysis of embedding in difference of image pixel pairs by neural network




In this paper a steganalysis method is proposed for pixel value differencing method. This steganographic method, which has been immune against conventional attacks, performs the embedding in the difference of the values of pixel pairs. Therefore, the histogram of the differences of an embedded image is di_erent as compared with a cover image. A number of characteristics are identified in the difference histogram that show meaningful alterations when an image is embedded. Five distinct multilayer perceptrons neural networks are trained to detect different levels of embedding. Every image is fed in to all networks and a voting system categorizes the image as stego or cover. The implementation results indicate an 88.6% success in correct categorization of the test images.


[1] S. Dumitrescu, X. Wu, and Z. Wang. Detection of LSB Steganography via Sample Pair Analysis. IEEE Transactions on Signal Processing, 51(7):1995-2007, 2003.

[2] N. Hopper. Toward a Theory of Steganography. PhD thesis, School of Computer Science, Carnegie Mellon University, 2004.

[3] N. Provos and P. Honeyman. Hide and Seek: An Introduction to Steganography. IEEE Security & Privacy, pages 32-44, 2003.

[4] B.Pitzmann. Information Hiding Terminology. In Information Hiding, volume 1174 of Lecture Notes in Computer Science, pages 347-350, Cambridge, U.K., 1996. Springer.

[5] M. Kharrazi, H.T. Sencar, and N. Memon. Image Steganography: Concepts and Practice. WSPC/ Lecture Notes Series, 2004.

[6] A. Westfeld. F5 a Steganographic Algorithm: High Capacity Despite Better Steganalysis. In Proceedings of the 4th International Information Hiding Workshop, volume 2137, pages 289-302. Springer-Verlag, 2001.

[7] M. Swanson, M. Kobayashi, and A. Tew_k. Multimedia Data Embedding and Watermarking Technologies. Proceedings of the IEEE, 86(6):1064-1087, 1998.

[8] I. Cox, J. Kilian, T. Leighton, and T. Shamoon. Secure Spread Spectrum Watermarking for Multimedia. IEEE Transactions on Image Processing, 6(12):1673-1687, 1997.

[9] N. Provos. Defending against statistical steganalysis. In the 10th USENIX Security Symposium, pages 323-335, 2001.

[10] A. Westfeld and A. P_tzman. Attacks on Steganographic Systems. In Proceedings of the 3rd International Information Hiding Workshop, pages 61-76. Springer-Verlag, 1999.

[11] J. Fridrich, M. Goljan, and R. Du. Reliable Detection of LSB Steganography in Grayscale and Color Images. In Proceedings of the ACM Special Session on Multimedia Security and Watermarking, pages 27-30, 2001.

[12] D.C. Wu and W.H. Tsai. A Steganographic Method for Images by Pixel-Value Differencing. Pattern Recognition Letters, 24:1613-1626, 2003.

[13] H.C. Wu, N.I. Wu, C.S. Tsai, and M.S. Hwang. Image Steganographic Scheme Based on Pixel-Value Differencing and LSB Replacement Methods. IEEE Proceedings Vision, Image and Signal Processing, 152(5):611-615, 2005.

[14] V. Sabeti, S. Samavi, M. Mahdavi, and S. Shirani. Steganalysis of Pixel-Value Di_erencing Steganographic Method. In Proceedings of the IEEE Paci_c Rim Conference on Communications, Computers and Signal Processing, pages 292-295, 2007.

[15] X. Zhang and S. Wang. Vulnerability of Pixel-Value Di_erencing Steganography to Histogram Analysis and Modi_cation for Enhanced Security. Pattern Recognition Letters, (3):331-339, 2004.

[16] H. Farid. Detecting Steganographic Message in Digital Images. Technical report, Dartmouth College, 2001.

[17] J. Fridrich. Feature-based Steganalysis for JPEG Images and its Implications for Future Design of Steganographic Schemes. In Proceedings of the 6th International Workshop on Information Hiding, volume 3200 of LNCS, pages 67-81, 2004.

[18] T. Holotyak, J. Fridrich, and S. Voloshynovskiy. Blind Statistical Steganalysis of Additive Steganography Using Wavelet Higher Order Statistics. In Proceedings of the 9th IFIP TC-6 TC-11 Conference on Communications and Multimedia Security, volume 3677 of LNCS, pages 273-274, 2005.

[19] J. Fridrich and T. Pevny. MultiClass Blind Steganalysis for JPEG Images. In SPIE Electronic Imaging, Security, Steganography and Watermarking of Multimedia Contents, volume 8, pages 257-269, 2006.

[20] Y. Q. Shi, G. Xuan, D. Zou, and J. Gao. Steganalysis Based on Moments of Characteristic functions Using Wavelet Decomposition, Prediction-Error Image, and Neural Network. In Proceedings of the IEEE International Conference on Multimedia and Expo, pages 269-272, 2005.

[21] J. Fridrich and T. Pevny. Merging Markov and DCT Features for Multi-Class JPEG Steganalysis. In the SPIE Electronic Imaging, pages 3-4, Photonics West, 2007.

[22] Q. Liu, A.H. Sung, Z. Chen, and J. Xu. Feature Mining and Pattern Classi_cation for Steganalysis of LSB Matching Steganography in Grayscale Images. Pattern Recognition, 41:56-66, 2008.

[23] T. Zhang and X. Ping. A New Approach to Reliable Detection of LSB Steganography in Natural Images. Signal Processing, 83:2085-2093, 2003.

[24] M.T. Hagan, H.B. Demuth, and M. Beale. Neural Network Design. PWS Publishing, Boston, 1996.

[25] A.D. Ker. Quantitative Evaluation of Pairs and RS Steganalysis. SPIE Security, Steganography, Watermarking Multimedia Contents, 5306:83-97, 2004.