Advantages of using feature selection techniques on steganalysis schemes

Authors:
Yoan Miche;Patrick Bas;Amaury Lendasse;Christian Jutten;Olli Simula
Affiliations:
Helsinki University of Technology, Laboratory of Computer and Information Science, Finland and INPG, Laboratoire des Images et des Signaux, Grenoble cedex, France;Helsinki University of Technology, Laboratory of Computer and Information Science, Finland and INPG, Laboratoire des Images et des Signaux, Grenoble cedex, France;Helsinki University of Technology, Laboratory of Computer and Information Science, Finland;INPG, Laboratoire des Images et des Signaux, Grenoble cedex, France;Helsinki University of Technology, Laboratory of Computer and Information Science, Finland
Venue:
IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
Year:
2007

Citing 6
Cited 0

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Defending against statistical steganalysis

SSYM'01 Proceedings of the 10th conference on USENIX Security Symposium - Volume 10
A Direct Method of Nonparametric Measurement Selection

IEEE Transactions on Computers
Feature-Based steganalysis for JPEG images and its implications for future design of steganographic schemes

IH'04 Proceedings of the 6th international conference on Information Hiding
The curse of dimensionality in data mining and time series prediction

IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
A feature selection methodology for steganalysis

MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security

Quantified Score

Hi-index	0.00

Visualization

Abstract

Steganalysis consists in classifying documents as steganographied or genuine. This paper presents a methodology for steganalysis based on a set of 193 features with two main goals: determine a sufficient number of images for effective training of a classifier in the obtained high-dimensional space, and use feature selection to select most relevant features for the desired classification. Dimensionality reduction is performed using a forward selection and reduces the original 193 features set by a factor of 13, with overall same performance.