Abstract
Image steganalysis is a very important research topic in the field of information security. The existing feature based image steganalysis methods have achieved the appealing performance. The performance of them greatly depends on the quality of the hand-crafted steganalysis feature vectors, such as Cartesian Calibration PEV (CC-PEV), DCT Residuals (DCTR), and so on. However, these feature vectors may contain some redundant elements that will reduce the discrimination power and increase the computation cost. In this paper, a novel feature selection model is proposed for JPEG image steganalysis. Specifically, the proposed model imposes an \(l_{2,1}\)-structural constraint on the projection matrix for feature selection. Further, to make the model insensitive to noises and outliers, a capped \(l_2\)-norm based loss function is adopted. Moreover, a graph-based manifold regularization term which exploits the intrinsic local geometric structure of the data is added into the objective function to select the effective feature elements. Finally, an alternately iterative optimization algorithm with proven convergence is given to solve the proposed model. The extensive experiments on three state-of-the-art JPEG steganographic algorithms with 0.1 and 0.2 embedding rates and two JPEG quality factors show that the proposed model can effectively remove some irrelevant and redundant elements meanwhile retaining high detection accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pevný, T., Filler, T., Bas, P.: Using high-dimensional image models to perform highly undetectable steganography. In: Böhme, R., Fong, P.W.L., Safavi-Naini, R. (eds.) IH 2010. LNCS, vol. 6387, pp. 161–177. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-16435-4_13
Denemark, T., Fridrich, J.: Steganography with multiple JPEG images of the same scene. IEEE Trans. Inf. Forensics Secur. 12(10), 2308–2319 (2017)
Kodovský, J., Fridrich, J.: Calibration revisited. In: 11th Multimedia and Security Workshop (MMSec), New Jersey, USA, pp. 63–74. ACM (2009)
Kodovský, J., Fridrich, J.: Steganalysis of JPEG images using rich models. In: SPIE 8303, Media Watermarking, Security, and Forensics, p. 83030A. SPIE (2012)
Holub, V., Fridrich, J.: Low complexity features for JPEG steganalysis using undecimated DCT. IEEE Trans. Inf. Forensics Secur. 10(2), 219–228 (2015)
Song, X., Liu, F., Yang, C., Luo, X., Zhang, Y.: Steganalysis of adaptive JPEG steganography using 2D Gabor filters. In: 3rd ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec), Portland, Oregon, USA, pp. 15–23. ACM (2015)
Xia, C., Guan, Q., Zhao, X., Xu, Z., Ma, Y.: Improving GFR steganalysis features by using Gabor symmetry and weighted histograms. In: 5th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec), Philadelphia, Pennsylvania, USA, pp. 55–66. ACM (2017)
Mohammadi, F.G., Abadeh, M.S.: Image steganalysis using a bee colony based feature selection algorithm. Eng. Appl. Artif. Intell. 31, 35–43 (2014)
Chhikara, R.R., Sharma, P., Singh, L.: A hybrid feature selection approach based on improved PSO and filter approaches for image steganalysis. Int. J. Mach. Learn. Cybern. 7(6), 1195–1206 (2016). https://doi.org/10.1007/s13042-015-0448-0
Adeli, A., Broumandnia, A.: Image steganalysis using improved particle swarm optimization based feature selection. Appl. Intell. 48, 1609–1622 (2018). https://doi.org/10.1007/s10489-017-0989-x
Pathak, Y., Arya, K.V., Shailendra, T.: Feature selection for image steganalysis using levy flight-based grey wolf optimization. Multimedia Tools Appl. 78, 1473–1494 (2019). https://doi.org/10.1007/s11042-018-6155-6
Ma, Y., Luo, X., Li, X., Bao, Z., Zhang, Y.: Selection of rich model steganalysis features based on decision rough set \(\alpha \)-positive region reduction. IEEE Trans. Circuits Syst. Video Technol. 29(2), 336–350 (2018)
Du, A., Ma, Y., Li, S., Ma, Y.: Robust unsupervised feature selection via matrix factorization. Neurocomputing 241, 115–127 (2017)
Lan, G., Hou, C., Nie, F., Luo, T., Yi, D.: Robust feature selection via simultaneous capped norm and sparse regularizer minimization. Neurocomputing 283, 228–240 (2018)
Tang, C., Liu, X., Li, M.: Robust unsupervised feature selection via dual self-representation and manifold regularization. Knowl. Based Syst. 145, 109–120 (2018)
Zheng, W., Yan, H., Yang, J., Yang, J.: Robust unsupervised feature selection by nonnegative sparse subspace learning. Neurocomputing 334, 156–171 (2019)
Yang, M., Cheng, D., Nie, F.: Adaptive-weighting discriminative regression for multi-view classification. Pattern Recogn. 88, 236–245 (2019)
Nie, F., Huang, H., Cai, X., Ding, C.: Efficient and robust feature selection via joint \(L_{2,1}\)-norms minimization. In: 23rd International Conference on Neural Information Processing Systems (NIPS), Vancouver, BC, Canada, pp. 1813–1821. Curran Associates Inc. (2010)
Zhu, X., Li, X., Zhang, S.: Block-row sparse multiview multilabel learning for image classification. IEEE Trans. Cybern. 46(2), 450–461 (2016)
Huang, S., Zhao, K., Xu, Z.: Self-weighted multi-view clustering with soft capped norm. Knowl. Based Syst. 158, 1–8 (2018)
Kodovský, J., Fridrich, J., Holub, V.: Ensemble classifiers for steganalysis of digital media. IEEE Trans. Inf. Forensics Secur. 7(2), 432–444 (2012)
Fridrich, J., Pevný, T., Kodovsky, J.: Statistically undetectable JPEG steganography: dead ends challenges, and opportunities. In: 9th Multimedia and Security Workshop (MMSec), Dallas, Texas, USA, pp. 3–14. ACM (2007)
Guo, L., Ni, J., Shi, Y.Q.: Uniform embedding for efficient JPEG steganography. IEEE Trans. Inf. Forensics Secur. 9(5), 814–825 (2014)
Holub, V., Fridrich, J., Denemark, T.: Universal distortion function for steganography in an arbitrary domain. EURASIP J. Inf. Secur. 2014, 1–13 (2014)
Acknowledgements
The work is supported by the National Natural Science Foundation of China (Grant No. 61872368). The authors gratefully acknowledge the helpful comments and suggestions of the reviewers, which have improved the presentation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
Proof of Theorem 1. According to the step \(\mathbf {1}\) of Algorithm 1 in the t-th iteration and Eq. (11), we have
which indicates that
According to Eq. (12), the following equations hold:
Thus, Eq. (18) can be transformed into the following form:
Further, the above inequality can be rewritten as
By replacing a and b in Lemma 1 with \(\Vert \varvec{w}^i_{(t+1)}\Vert _2^2\) and \(\Vert \varvec{w}^i_{(t)}\Vert _2^2\), we get
By adding Eqs. (22) and (23) on both sides (note that Eq. (23) is repeated for \(1\le i \le d\)), we have
That is to say,
Since the values of objective function (7) decrease monotonously and are greater than zeros, so Algorithm 1 is convergent. Theorem 1 is proven.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, L., Zhong, J., Zhong, P., Xue, Y., Wen, J. (2020). A Novel Feature Selection Model for JPEG Image Steganalysis. In: Wang, H., Zhao, X., Shi, Y., Kim, H., Piva, A. (eds) Digital Forensics and Watermarking. IWDW 2019. Lecture Notes in Computer Science(), vol 12022. Springer, Cham. https://doi.org/10.1007/978-3-030-43575-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-43575-2_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43574-5
Online ISBN: 978-3-030-43575-2
eBook Packages: Computer ScienceComputer Science (R0)