Blind Quantitative Steganalysis Based on Feature Fusion and Gradient Boosting

Blind quantitative steganalysis is about revealing more details about hidden information without any prior knowledge of steganograghy. Machine learning can be used to estimate some properties of hidden message for blind quantitative steganalysis. We propose a quantitative steganalysis method based on fusion of different steganalysis features and the estimator relies on gradient boosting. Experimental result shows that our proposed method has good performance for quantitative steganalysis.

[1]  Chein-I Chang,et al.  Variants of Principal Components Analysis , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[2]  Tomás Pevný,et al.  Multiclass Detector of Current Steganographic Methods for JPEG Format , 2008, IEEE Transactions on Information Forensics and Security.

[3]  Bin Li,et al.  Steganalysis of YASS , 2009, IEEE Trans. Inf. Forensics Secur..

[4]  Jessica J. Fridrich,et al.  Quantitative steganalysis of digital images: estimating the secret message length , 2003, Multimedia Systems.

[5]  Jessica J. Fridrich,et al.  Steganalysis of JPEG Images: Breaking the F5 Algorithm , 2002, Information Hiding.

[6]  Xuezeng Pan,et al.  Feature-Based Steganalysis for JPEG Images , 2009, 2009 International Conference on Digital Image Processing.

[7]  Edward J. Delp,et al.  Media Forensics and Security , 2009 .

[8]  Trevor Hastie,et al.  Additive Logistic Regression : a Statistical , 1998 .

[9]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[10]  Tomás Pevný,et al.  From Blind to Quantitative Steganalysis , 2012, IEEE Trans. Inf. Forensics Secur..

[11]  Tomás Pevný,et al.  From Blind to Quantitative Steganalysis , 2009, IEEE Transactions on Information Forensics and Security.

[12]  Xiaogang Wang,et al.  A unified framework for subspace face recognition , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  M. Bartlett.  Further aspects of the theory of multiple regression , 1938, Mathematical Proceedings of the Cambridge Philosophical Society.

[14]  Yun Q. Shi,et al.  A Markov Process Based Approach to Effective Attacking JPEG Steganography , 2006, Information Hiding.