Robust steganalysis based on training set construction and ensemble classifiers weighting

The cover source mismatch problem in steganalysis is a serious problem which keeps current steganalysis from practical use. It is mainly because of the high intra-class variation of cover and stego samples in the feature space, since current steganalytic features are inevitably affected much by the image content, size, quality and many other factors. Small training set often reflects only part of the real data distribution, hence the classifier (steganalyzer) may be undertrained and lack of robustness. In this paper, we propose a scheme to efficiently construct large representative training set for steganalysis. We also scheme out weighted ensemble classifiers which can be adaptive to testing data. Experimental results show that our method can improve the performance and robustness of ste-ganalysis under high intra-class variation.

[1]  Xiaofeng Li,et al.  Generalized transfer component analysis for mismatched JPEG steganalysis , 2013, 2013 IEEE International Conference on Image Processing.

[2]  Jessica J. Fridrich,et al.  Calibration revisited , 2009, MM&Sec '09.

[3]  Huan Liu,et al.  On Issues of Instance Selection , 2002, Data Mining and Knowledge Discovery.

[4]  Jessica J. Fridrich,et al.  Study of cover source mismatch in steganalysis and ways to mitigate its impact , 2014, Electronic Imaging.

[5]  Jessica J. Fridrich,et al.  Ensemble Classifiers for Steganalysis of Digital Media , 2012, IEEE Transactions on Information Forensics and Security.

[6]  Yun Q. Shi,et al.  JPEG image steganalysis utilizing both intrablock and interblock correlations , 2008, 2008 IEEE International Symposium on Circuits and Systems.

[7]  Cordelia Schmid,et al.  Transformation Pursuit for Image Classification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Tomás Pevný,et al.  Steganalysis by Subtractive Pixel Adjacency Matrix , 2009, IEEE Transactions on Information Forensics and Security.

[9]  Mauro Barni,et al.  Forensics aided steganalysis of heterogeneous images , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  Tomás Pevný,et al.  Merging Markov and DCT features for multi-class JPEG steganalysis , 2007, Electronic Imaging.

[11]  Jessica J. Fridrich,et al.  Rich Models for Steganalysis of Digital Images , 2012, IEEE Transactions on Information Forensics and Security.

[12]  Ingemar J. Cox,et al.  A comparative study of ± steganalyzers , 2008, 2008 IEEE 10th Workshop on Multimedia Signal Processing.

[13]  Andrew D. Ker,et al.  Going from small to large data in steganalysis , 2012, Other Conferences.

[14]  Andrew D. Ker,et al.  Steganalysis with mismatched covers: do simple classifiers help? , 2012, MM&Sec '12.

[15]  Klaus Brinker,et al.  Incorporating Diversity in Active Learning with Support Vector Machines , 2003, ICML.

[16]  Jessica J. Fridrich,et al.  Steganalysis in resized images , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[17]  FridrichJessica,et al.  Rich Models for Steganalysis of Digital Images , 2012 .

[18]  Jessica J. Fridrich,et al.  Effect of Image Downsampling on Steganographic Security , 2014, IEEE Transactions on Information Forensics and Security.

[19]  Jessica J. Fridrich,et al.  Steganalysis of JPEG images using rich models , 2012, Other Conferences.

[20]  Tomás Pevný,et al.  A mishmash of methods for mitigating the model mismatch mess , 2014, Electronic Imaging.

[21]  Tomás Pevný,et al.  Statistically undetectable jpeg steganography: dead ends challenges, and opportunities , 2007, MM&Sec.

[22]  Qingzhong Liu,et al.  Steganalysis of DCT-embedding based adaptive steganography and YASS , 2011, MM&Sec '11.