Abstract
In order to enhance the detection rate of ensemble classifiers in steganalysis, concern the problems that the accuracy of basic classifier is low and the kind of basic classifier is single in typical ensemble classifiers, an algorithm based on rotating forest transformation and multiple classifiers ensemble is proposed. First, some feature subsets generated randomly merger with training sample to generate sample subsets, then the sample subset is transformed by rotating forest algorithm and train some basic classifiers, which is made of fisher linear discriminate, extreme learning machine and support vector machine with weighted voting. At last, the majority voting method is used to integrate the decisions of base classifiers. Experimental results show that by different steganography approaches and in different embedding rate conditions, the error rate of proposed method decreased by 3.2% and 1.1% in compared with the typical ensemble classifiers and ensemble classifiers of extreme learning machines, therefore demonstrating the proposed method could improve the detection accuracy of ensemble classifier.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sedighi, V., Fridrich, J.: Effect of saturated pixels on security of steganographic schemes for digital images. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 2747–2751. IEEE, September 2016
Tang, W., Li, H., Luo, W., Huang, J.: Adaptive steganalysis based on embedding probabilities of pixels. IEEE Trans. Inf. Forensics Secur. 11(4), 734–745 (2016)
Li, F., Wu, K., Lei, J., Wen, M., Bi, Z., Gu, C.: Steganalysis over large-scale social networks with high-order joint features and clustering ensembles. IEEE Trans. Inf. Forensics Secur. 11(2), 344–357 (2016)
Filler, T., Judas, J., Fridrich, J.: Minimizing additive distortion in steganography using syndrome-trellis codes. IEEE Trans. Inf. Forensics Secur. 6(3), 920–935 (2011)
Fridrich, J., Kodovsky, J.: Rich models for steganalysis of digital images. IEEE Trans. Inf. Forensics Secur. 7(3), 868–882 (2012)
Kodovsky, J., Fridrich, J., Holub, V.: Ensemble classifiers for steganalysis of digital media. IEEE Trans. Inf. Forensics Secur. 7(2), 432–444 (2012)
Kodovský, J.: Steganalysis of digital images using rich image representations and ensemble classifiers. Doctoral dissertation, State University of New York (2012)
Zhang, M.Q., Di, F.Q., Liu, J.: Universal steganalysis based on selective ensemble classifier. J. Sichuan Univ. 47(1), 36–44 (2015)
Li, F.Y., Zhang, X.P.: Steganalysis for color images based on channel co-occurrence and selective ensemble. J. Image Graph. 20(5), 609–617 (2015)
Sachnev, V., Ramasamy, S., Sundaram, S., Kim, H.J., Hwang, H.J.: A cognitive ensemble of extreme learning machines for steganalysis based on risk-sensitive hinge loss function. Cogn. Comput. 7(1), 103–110 (2015)
Cogranne, R., Fridrich, J.: Modeling and extending the ensemble classifier for steganalysis of digital images using hypothesis testing theory. IEEE Trans. Inf. Forensics Secur. 10(12), 2627–2642 (2015)
Rodriguez, J.J., Kuncheva, L.I., Alonso, C.J.: Rotation forest: a new classifier ensemble method. IEEE Trans. Pattern Anal. Mach. Intell. 28(10), 1619–1630 (2006)
Denemark, T., Fridrich, J., Holub, V.: Further study on the security of S-UNIWARD. In: IS&T/SPIE Electronic Imaging, p. 902805. International Society for Optics and Photonics, February 2014
Li, B., Wang, M., Huang, J.: A new cost function for spatial image steganography. In: Proceedings of IEEE International Conference on Image Processing, pp. 27–30 (2014)
Holub, V., Fridrich, J.: Designing steganographic distortion using directional filters. In: 2012 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 234–239. IEEE, December 2012
Wang, X.X.: Research on classifier selective ensemble method and their diversity measurement. Master dissertation, Lanzhou University of Technology (2011)
Mao, S.S., Xiong, L., Jiao, L.C., Zhang, S., Chen, B.: Isomerous multiple classifier ensemble via transformation of the rotating forest. J. Xidian Univ. 41(5), 48–53 (2014)
Li, X., Zhao, H.: Weighted random subspace method for high dimensional data classification. Stat. Interface 2(2), 153 (2009)
Pevný, T., Filler, T., Bas, P. (eds.): Break Our Steganographic System. http://boss.gipsa-lab.grenobleinp.fr
Acknowledgments
This work was supported in part by the National Nature Science Foundation of China (Grant Nos. U1636114, 61402531, 61572521, 61379152) and the Nature Science Basic Research Plan in Shaanxi Province of China (Grant Nos. 2014JM8300, 2014JQ8358, 2015JQ6231, 2016JQ6037) and the Public Welfare Research Project of Guangdong Province (Grant Nos. 2014A010103031).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Cao, Z., Zhang, M., Chen, X., Sun, W., Shan, C. (2018). An Image Steganalysis Algorithm Based on Rotation Forest Transformation and Multiple Classifiers Ensemble. In: Barolli, L., Zhang, M., Wang, X. (eds) Advances in Internetworking, Data & Web Technologies. EIDWT 2017. Lecture Notes on Data Engineering and Communications Technologies, vol 6. Springer, Cham. https://doi.org/10.1007/978-3-319-59463-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-59463-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59462-0
Online ISBN: 978-3-319-59463-7
eBook Packages: EngineeringEngineering (R0)