KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

New Blind Steganalysis Framework Combining Image Retrieval and Outlier Detection

  • Wu, Yunda (Zhengzhou Information Science and Technology Institute) ;
  • Zhang, Tao (Zhengzhou Information Science and Technology Institute) ;
  • Hou, Xiaodan (Zhengzhou Information Science and Technology Institute) ;
  • Xu, Chen (Zhengzhou Information Science and Technology Institute)
  • Received : 2016.05.07
  • Accepted : 2016.11.15
  • Published : 2016.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The detection accuracy of steganalysis depends on many factors, including the embedding algorithm, the payload size, the steganalysis feature space and the properties of the cover source. In practice, the cover source mismatch (CSM) problem has been recognized as the single most important factor negatively affecting the performance. To address this problem, we propose a new framework for blind, universal steganalysis which uses traditional steganalyst features. Firstly, cover images with the same statistical properties are searched from a reference image database as aided samples. The test image and its aided samples form a whole test set. Then, by assuming that most of the aided samples are innocent, we conduct outlier detection on the test set to judge the test image as cover or stego. In this way, the framework has removed the need for training. Hence, it does not suffer from cover source mismatch. Because it performs anomaly detection rather than classification, this method is totally unsupervised. The results in our study show that this framework works superior than one-class support vector machine and the outlier detector without considering the image retrieval process.

Keywords

References

  1. J. Kodovsky, J. Fridrich, and V. Holub, "Ensemble Classifiers for Steganalysis of Digital Media," IEEE Transactions on Information Forensics and Security, vol. 7, no. 2, pp. 432-444, 2012. https://doi.org/10.1109/TIFS.2011.2175919
  2. V. Holub and J. Fridrich, "Random projections of residuals for digital image steganalysis," IEEE Trans. Inf. Forensics Security, vol. 8, no. 12, pp. 1996−2006, Dec. 2013.
  3. P. Bas, T. Filler, and T. Pevny, "Break our steganographic system: The ins and outs of organizing BOSS," in Proc. of 13th Information Hiding conference, pp. 59-70, 2011.
  4. I. Lubenko and A. D. Ker, "Steganalysis with mismatched covers: Do simple classifiers help," in Proc. of 13th Workshop, Multimedia Security, pp. 11-18, 2012.
  5. M. Barni, G. Cancelli, and A. Esposito, "Forensics aided steganalysis of heterogeneous images," in Proc. of IEEE Int. Conf. Acoustic Speech and Signal Processing, pp. 1690-1693, 2010.
  6. S. Lyu and H. Farid, "Steganalysis using color wavelet statistics and one-class vector support machines," in Proc. of SPIE, Security, Steganography, Watermarking of Multimedia Contents VI, vol. 5306, Jun. 2004.
  7. T. Pevny and J. Fridrich, "Novelty detection in blind steganalysis," in Proc. of 10th Workshop, Multimedia Security, pp. 167-176, 2008.
  8. I. Lubenko and A. D. Ker, "Going from small to large data in steganalysis," in Proc. of IS&T/SPIE Electron. Image, vol. 8303, p. 83030M, Feb. 2012.
  9. G. Cancelli, G. Doerr, I. Cox, and M. Barni, "A comparative study of ${\pm}1$ steganalyzers," in Proc. of IEEE Int. Workshop, Multimedia Signal Processing, pp. 791-796, 2008.
  10. T. Pevny and J. Fridrich, "Multiclass detector of current steganographic methods for JPEG format," IEEE Trans. Inf. Forensics Security, vol. 4, no. 3, pp. 635-650, Dec. 2008.
  11. X. Hou, T. Zhang, and G. Xiong et al., "Forensics aided steganalysis of heterogeneous bitmap images with different compression history," Ksii Transactions on Internet & Information Systems, vol. 6, no. 8, pp. 1926-1945, Aug. 2012. https://doi.org/10.3837/tiis.2012.08.003
  12. X. Hou, T. Zhang, and G. Xiong et al., "A novel steganalysis framework of heterogeneous images based on GMM clustering," Signal Process: Image Communication, vol. 29, no. 3, pp. 385-399, Mar. 2014. https://doi.org/10.1016/j.image.2014.01.006
  13. S. Cho, M. Gawecki, and C. Kuo, "Content-dependent feature selection for block-based image steganalysis," in Proc. of IEEE Int. Symposium on Circuits and Systems, pp. 1416-1419, 2012.
  14. S. Cho, B. Cha, and M. Gawecki et al., "Block-based image steganalysis: Algorithm and performance evaluation," Journal of Visual Communication & Image Representation, vol. 24, no. 7, pp. 846-856, Oct. 2013. https://doi.org/10.1016/j.jvcir.2013.05.007
  15. X. Li, X. Kong, B. Wang, Y. Guo, and X. You, "Generalized transfer component analysis for mismatched JPEG steganalysis," in Proc. of IEEE Int. Conf. Image Processing, pp. 4432-4436, 2013.
  16. A. D. Ker and T. Pevny, "A new paradigm for steganalysis via clustering," in Proc. of SPIE - The International Society for Optical Engineering, vol.7880, Feb. 2011.
  17. A. D. Ker and T. Pevny, "Identifying a steganographer in realistic and heterogeneous data sets," in Proc. of IS&T/SPIE Electronic Imaging. International Society for Optics and Photonics, vol. 8303, pp. N01-N13, May 2012.
  18. A. D. Ker and T. Pevny, "The steganographer is the outlier: Realistic large-scale steganalysis," IEEE Trans. Inf. Forensics Security, vol. 9, no.9, pp. 1424-1435, Sep. 2014. https://doi.org/10.1109/TIFS.2014.2336380
  19. W. Ng, Z. He, D. Yeung, and P. Chan, "Steganalysis classifier training via minimizing sensitivity for different imaging sources," Inform. Science, vol. 281, pp. 211-224, May. 2014. https://doi.org/10.1016/j.ins.2014.05.028
  20. J. Kodovsky, V. Sedighi and J. Fridrich, "Study of cover source mismatch in steganalysis and ways to mitigate its impact," in Proc. of SPIE, Media Watermark., Security, and Forensics, vol. 9028, p. 90280J, Feb. 2014.
  21. T. Pevny and A. D. Ker, "A mishmash of methods for mitigating the model mismatch mess," in Proc. of SPIE, Media Watermark., Security, and Forensics, vol. 9028, p. 90280I, Feb. 2014.
  22. Kharrazi, M., H. T. Sencar, and N. Memon. "Blind source camera identification," in Proc. of IEEE Int. Conf. Image Processing, pp. 709-712, 2004.
  23. Filler, T., J. Fridrich, and M. Goljan. "Using sensor pattern noise for camera model identification," in Proc. of IEEE Int. Conf. Image Processing, pp. 1296-1299, 2008.
  24. J. Lukas, J. Fridrich, and M. Goljan. "Determining digital image origin using sensor imperfections," in Proc. of SPIE, Image and Video Communications and Processing, vol. 5685, pp. 249-260, 2005.
  25. M. Goljan, Miroslav, J. Fridrich, and T. Filler. "Large scale test of sensor fingerprint camera identification," in Proc. of SPIE, Media Forensics and Security, vol. 7254, 2008.
  26. S. Gao, G. S. Xu, and R. M. Hu, "Camera model identification based on the characteristic of CFA and interpolation," in Proc. of International Conference on Digital-Forensics and Watermarking, vol. 7128, pp. 268-280. 2011.
  27. Magiera, P., Londahl, C.: ROF Denoising Algorithm (released 2008), http://www.mathworks.com/matlabcentral/fileexchange/22410-rof-denoising-algorithm/content/ ROFdenoise.m.
  28. Janssens, Jeroen H. M., I. Flesch, and E. O. Postma. "Outlier Detection with One-Class Classifiers from ML and KDD." in Proc. of International Conference on Machine Learning and Applications, pp. 147-153, 2009.
  29. M. M. Breunig, H. P. Kriegel, R. T. Ng, and J. Sander, "LOF: identifying density-based local outliers," in Proc. of ACM SIGMOD Int. Conf. Manage. Data, pp. 93-104, 2000.
  30. T. Gloe and R. Bohme, "The 'Dresden Image Database' for benchmarking digital image forensics," in Proc. of SAC, pp. 1584-1590. 2010.
  31. T. Pevny and J. Fridrich, "Merging Markov and DCT features for multi-class JPEG teganalysis," in Proc. of SPIE, Media Watermark., Security, Forensics IX, vol. 6505, pp. 3-14, Feb. 2007.
  32. K Yu, L Ji, X Zhang. "Kernel nearest-neighbor algorithm," Neural Processing Letters, pp. 147-156, 20002.
  33. S. Gao, "A Hybrid Approach for Camera-Model Detection," International Journal of Security and Its Applications, 2015, Vol. 9, no. 8.
  34. V. Holub, J. Fridrich and T. Denemark, "Universal distortion function for steganography in an arbitrary domain," EURASIP Journal on Information Security, pp. 1-13, 2014.
  35. L. Guo, J. Ni, and Y. Q. Shi, "An efficient JPEG steganographic scheme using uniform embedding," IEEE Transactions on Information Forensics and Security, vol.9, pp. 169-174, 2012.
  36. V. Holub and J. Fridrich, "Low Complexity Features for JPEG Steganalysis Using Undecimated DCT," IEEE Transactions on Information Forensics and Security, Vol. 10, no. 2, 2015.