Domain Adaptation for Video Steganalysis against Motion Vector Based Steganography

Abstract:

Video steganalysis takes effect when videos corrupted by the target steganography method are available. Nevertheless, classical classifiers deteriorate in the opposite case. This paper presents a method to cope with the problem of steganography method mismatch for the detection of motion vector (MV) based steganography. Firstly, Adding-or-Subtracting-One (AoSO) feature against MV based steganography and Transfer Component Analysis (TCA) for domain adaptation are revisited. Distributions of AoSO feature against various MV based steganography methods are illustrated, followed by the potential effect of TCA based AoSO feature. Finally, experiments are carried out on various cases of steganography method mismatch. Performance results demonstrate that TCA+AoSO feature significantly outperforms AoSO feature, and is more favorable for real-world applications.

• Periodical: Advanced Materials Research (Volumes 998-999)
• Pages: 1138-1145
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.998-999.1138
• Online since: July 2014
• Authors: Ke Ren Wang*, Wen Xiang Li
• Keywords: AoSO, Domain Adaptation, Motion Vector, TCA, Video Steganalysis

References

[1] K. Wang, H. Zhao, and H. Wang, Video Steganalysis Against Motion Vector-Based Steganography by Adding or Subtracting One Motion Vector Value, IEEE Transactions on Information Forensics and Security, vol. 9, no. 5, 2014, pp.741-751.

DOI: 10.1109/tifs.2014.2308633

[2] OpenPuff Steganography & Watermarking [Online], Available: http: /embeddedsw. net/OpenPuff_Steganography_Home. html, accessed May, (2014).

[3] J. Fridrich, J. Kodovsky, Rich Models for Steganalysis of Digital Images, IEEE Transactions on Information Forensics and Security, vol. 7, no. 3, 2012, pp.868-882.

DOI: 10.1109/tifs.2012.2190402

[4] W. Luo, Y. Wang, and J. Huang, Security analysis on spatial ±1 steganography for JPEG decompressed images, IEEE Signal Processing Letters, vol. 18, no. 1, 2011, pp.39-42.

DOI: 10.1109/lsp.2010.2091127

[5] MSU Stegovideo [Online], Available: http: /compression. ru/video/ stego_video/index_en. html, accessed May, (2014).

[6] M. Kutter, F. Jordan, and T. Ebrahimi, Proposal of A Watermarking Technique For Hiding/retrieving Data in Compressed and Decompressed Video, Technical report M2281, ISO/IEC document, JTC1/SC29/WG11, (1997).

[7] C. Xu, X. Ping, and T. Zhang, Steganography in Compressed Video Stream, Proc. of the First International Conference on Innovative Computing, Information and Control, 2006, pp.269-272.

DOI: 10.1109/icicic.2006.158

[8] D. Y. Fang, L. W. Chang, Data Hiding For Digital Video with Phase of Motion Vector, Proc. of IEEE International Symposium on Circuits and Systems, 2006, p.1422–1425.

DOI: 10.1109/iscas.2006.1692862

[9] H. Aly, Data Hiding in Motion Vectors of Compressed Video Based on Their Associated Prediction Error, IEEE Transactions on Information Forensics and Security, vol. 6, no. 1, 2011, pp.14-18.

DOI: 10.1109/tifs.2010.2090520

[10] Y. Cao, X. Zhao, D. Feng, and R. Sheng, Video Steganography with Perturbed Motion Estimation", Proc. of IH, 11, Lecture Notes in Computer Science, vol. 6958, 2011, pp.193-207.

DOI: 10.1007/978-3-642-24178-9_14

[11] G. B. Yang, J. J. Li, Y. L. He, and Z. W. Kang, An Information Hiding Algorithm Based On Intra-prediction Modes and Matrix Coding for H. 264/AVC Video Stream, International Journal of Electronics and Communications, 2011, vol. 65, no. 4, pp.331-337.

DOI: 10.1016/j.aeue.2010.03.011

[12] C. T. Zhang, Y. T. Su, Information Hiding Based on Intra Prediction Modes for H. 264/AVC, Proc. of IEEE International Conference on Multimedia and Expo, 2007, pp.1231-1234.

DOI: 10.1109/icme.2007.4284879

[13] S. Bouchama, L. Hamami, and H. Aliane, H. 264/AVC Data Hiding Based on Intra Prediction Modes for Real-time Applications, Proc. of the World Congress on Engineering and Computer Science, 2012, pp.655-658.

DOI: 10.1109/icisa.2013.6579384

[14] C. S. Lu, J. R. Chen, K. C. Fan. Real-Time Frame-dependent Video Watermarking in VLC Domain. Signal Processing: Image Communication, 2005, vol. 20, no. 7, pp.624-642.

DOI: 10.1016/j.image.2005.03.012

[15] K. Liao, S. G. Lian, Z. C. Guo, J. L. Wang. Efficient Information Hiding in H. 264/AVC Video Coding. Telecommunication System, vol. 49, no. 2, 2012, pp.261-269.

DOI: 10.1007/s11235-010-9372-5

[16] U. Budhia, and D. Kundur, Digital Video Steganalysis Exploiting Collusion Sensitivity, Sensors, Command. Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense, Edward M. Carapezza, ed., Proc. SPIE, vol. 5403, 2004, pp.210-221.

DOI: 10.1117/12.540814

[17] U. Budhia, D. Kundur, and T. Zourntos, Digital Video Steganalysis Exploiting Statistical Visibility in The Temporal Domain, IEEE Transactions on Information Forensics and Security, vol. 1, no. 1, 2006, pp.43-55.

DOI: 10.1109/tifs.2006.885020

[18] V. Pankajakshan, G. Doërr, and P. K. Bora, Detection of Motion-Incoherent Components in Video Streams, IEEE Transactions on Information Forensics and Security, vol. 4, no. 1, 2009, pp.49-58.

DOI: 10.1109/tifs.2008.2012199

[19] S. Yu, H. X. Xu, Z. H. Yang, and Z. C. Li, A Novel Steganalysis Scheme of Digital Video, Proc. of 2010 International Conference on Multimedia Information Networking and Security, 2010, pp.952-956.

DOI: 10.1109/mines.2010.203

[20] J. Wu, R. Zhang, M. Chen, and X. Niu, Steganalysis of MSU StegoVideo Based on Discontinuous Coefficient, Proc. of 2nd International Conference on Computer Engineering and Technology, 2010, pp.96-99.

DOI: 10.1109/iccet.2010.5485297

[21] K. Wang, J. Han, H. Wang, Digital Video Steganalysis by Subtractive Prediction Error Adjacency Matrix, Multimedia Tools and Applications, 2013, in press, DOI: 10. 1007/s11042-013-1373-4.

DOI: 10.1007/s11042-013-1373-4

[22] Y. Su, C. Zhang, and C. Zhang, A Video Steganalytic Algorithm Against Motion-Vector-Based Steganography, Signal Processing, vol. 91, no. 8, 2011, p.1901-(1909).

DOI: 10.1016/j.sigpro.2011.02.012

[23] C. Q. Zhang, Y. T. Su, C. T. Zhang, A New Video Steganalysis Algorithm Against Motion Vector Steganography, Proc. of 4th International Conference on Wireless Communications, Networking and Mobile Computing, 2008, pp.1-4.

DOI: 10.1109/wicom.2008.781

[24] Y. Cao, X. Zhao, and D. Feng, Video Steganalysis Exploiting Motion Vector Reversion-based Features, IEEE Signal Processing letters, vol. 19, no. 1, January, 2012, pp.35-38.

DOI: 10.1109/lsp.2011.2176116

[25] A. D. Ker, P. Bas, R. Bohme, etc, Moving Steganography and Steganalysis from the Laboratory into the Real World, IH&MMSec'13, June 17–19, 2013, Montpellier, France.

[26] S. J. Pan, Q. Yang, A Survey on Transfer Learning, IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, October, 2010, pp.1345-1359.

[27] J. Huang, A. Smola, and A. Gretton, etc., Correcting Sample Selection Bias by Unlabeled Data, Proc. of 19th Ann. Conf. Neural Information Processing Systems, (2007).

[28] M. Long, J. Wang, and G. Ding, etc., Transfer Feature Learning with Joint Distribution Adaptation, IEEE International Conference on Computer Vision, Sydney, Australia, Dec. 2013, pp.2200-2207.

DOI: 10.1109/iccv.2013.274

[29] S. J. Pan, I. W. Tsang, J. T. Kwok, and Q. Yang, Domain Adaptation via Transfer Component Analysis, IEEE Transactions on Neural Networks, vol. 22, no. 2, February, 2011, pp.199-210.

DOI: 10.1109/tnn.2010.2091281

[30] J. Nam, S. J. Pan, and S. Kim, Transfer Defect Learning, Proc. of International Conference on Software Engineering, Piscataway, NJ, USA, 2013, pp.382-391.

[31] LIBLINEAR-A Library for Large Linear Classification [Online], Available: http: /www. csie. ntu. edu. tw/~cjlin/liblinear, accessed May, (2014).

[32] FFMPEG Library [Online], Available: http: /ffmpeg. sourceforge. net/, accessed October, (2013).

[33] VideoLAN-x264, the best H. 264/AVC encoder [Online], Available: http: /www. videolan. org/developers/x264. html, accessed May, (2014).