Modeling and Extending the Ensemble Classifier for Steganalysis of Digital Images Using Hypothesis Testing Theory
Authors:
- 19 August 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 10 (12) , 2627-2642
Abstract
The machine learning paradigm currently predominantly used for steganalysis of digital images works on the principle of fusing the decisions of many weak base learners. In this paper, we employ a statistical model of such an ensemble and replace the majority voting rule with a likelihood ratio test. This allows us to train the ensemble to guarantee desired statistical properties, such as the false-alarm probability and the detection power, while preserving the high detection accuracy of original ensemble classifier. It also turns out the proposed test is linear. Moreover, by replacing the conventional total probability of error with an alternative criterion of optimality, the ensemble can be extended to detect messages of an unknown length to address composite hypotheses. Finally, the proposed well-founded statistical formulation allows us to extend the ensemble to multi-class classification with an appropriate criterion of optimality and an optimal associated decision rule. This is useful when a digital image is tested for the presence of secret data hidden by more than one steganographic method. Numerical results on real images show the sharpness of the theoretically established results and the relevance of the proposed methodology.Keywords
Funding Information
- Conseil Régional Champagne Ardenne
- Air Force Office of Scientific Research (FA9950-12-1-0124)
This publication has 39 references indexed in Scilit:
- Statistical detection of data hidden in least significant bits of clipped imagesSignal Processing, 2014
- Universal distortion function for steganography in an arbitrary domainEURASIP Journal on Information Security, 2014
- A Cover Image Model For Reliable Steganalysis2011
- Statistical Decision Methods in Hidden Information DetectionLecture Notes in Computer Science, 2011
- Using High-Dimensional Image Models to Perform Highly Undetectable Steganography2010
- Batch Steganography and Pooled Steganalysis2007
- Detection of Hiding in the Least Significant BitIEEE Transactions on Signal Processing, 2004
- Computing Multivariate Normal Probabilities: A New LookJournal of Computational and Graphical Statistics, 2002
- Optimal simultaneous detection and estimation under a false alarm constraintIEEE Transactions on Information Theory, 1995
- A Simplex Method for Function MinimizationThe Computer Journal, 1965