Video Steganalysis Exploiting Motion Vector Calibration-Based Features

Abstract:

The motion vector (MV)-based steganography embeds the secret messages by modifying the motion vectors. So the traditional video steganalytic schemes cannot detect the presence of the hidden messages by MV-based steganography. In this paper, a novel calibration-based steganalytic scheme against MV-based steganography is presented. The features are derived from the shift differences between the original and calibrated MVs, and then the feature vector is constructed. Using the extracted feature vectors, the support vector machine (SVM) is trained to detect the presence of stego videos. Compared with other features, the proposed features have better performance even with the low embedding strength.

• Periodical: Advanced Materials Research (Volumes 482-484)
• Pages: 168-172
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.482-484.168
• Online since: February 2012
• Authors: Yu Deng, Yun Jie Wu, Lin Na Zhou
• Keywords: Calibration, Motion Vector, Steganalysis, Video

References

[1] M. Kutter, Y. Su and C. Zhang. Proposal of a watermarking technique for hiding/retrieving data in compressed and decompressed video, Technical Report M2281, ISO/IEC document, JTCI/SC29/WG11(1997).

[2] Yuanjun Dai, Lihe Zhang and Yixian Yang. A new method of MPEG video watermarking technology, in: Proceeding of ICCT2003, 1845-1847(2003).

DOI: 10.1109/icct.2003.1209886

[3] Jun Zhang, Henri Maitre, Jiegu Li and Ling Zhang. Embedding watermark in MPEG video sequences, in: IEEE Fourth Workshop on Multimedia Signal Processing, 535-540(2001)

DOI: 10.1109/mmsp.2001.962788

[4] H.Aly. IEEE Trans. Inf. Forensics Secur., 6(1), 14-18(2011).

[5] Y. Cao, X. Zhao, D. Feng and R.Sheng. Video steganography with perturbed motion estimation, in: Proceeding of Ih' ll , Lecture Notes in Computer Science, 193-207(2011)

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

[6] Y. Cao, X. Zhao and D. Feng. IEEE signal processing letters, 19(1), 35-38(2012).

[7] Y. Su, C. Zhang and C. Zhang. Signal Processing, 91, 1901-1909(2011).

[8] J. Fridrich, Feature-based steganalysis for JPEG images and its implications for future design of steganographic scheme, in : Proceeding of IH' 04, Lecture Notes in Computer Science, 67-81(2004).

DOI: 10.1007/978-3-540-30114-1_6

[9] Iain E. G. Richardson, H.264 and MPEG-4 Video Compression, John Wiley & Sons Ltd, 30-41(2003).

[10] J. Zheng, L. Chau. IEEE Transactions on Broadcasting, 49(4), 383-389(2003).

[11] C.J. Lin, LIBSVM-A library for support vector machine, http://www.csie.ntu.edu.tw/cjlin/libsvm 2 (2011).

[12] Available: http://www.xvid.org/, Xvid Codec 1.1.3(2009).