Binary Coded Genetic Algorithm with Ensemble Classifier for feature selection in JPEG steganalysis

Vasily Sachnev, Hyong Joong Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper, we propose a Binary Coded Genetic Algorithm with Ensemble Classification feature selection procedure designed for steganalysis. Proposed feature selection method was used for searching the most appropriate subset of features from 22510 dimension feature space superior for JPEG steganal-ysis. Reduced set of features shows better classification accuracy for JPEG steganalysis compared to complete set of features. In our method we used an ensemble classifier to approximate the functional relationship between the reduced feature set and class label. Search for optimal subset of features requires to solve two optimization problems: define the optimal number of features and define the optimal subset itself. Proposed Binary Coded Genetic algorithm enables to solve two optimization problems together. Each feature is coded as a binary coefficient in a binary string, which represent one solution of the feature selection problem. Genetic operations executed for binary strings (parents) results new binary strings (child) with good chance to have higher classification accuracy for JPEG steganalysis. Experimental results clearly indicate the advantage of using the proposed reduced set of features for JPEG steganalysis.

Original languageEnglish
Title of host publicationIEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings
PublisherIEEE Computer Society
ISBN (Print)9781479928439
DOIs
Publication statusPublished - 2014 Jan 1
Event9th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE ISSNIP 2014 - Singapore, Singapore
Duration: 2014 Apr 212014 Apr 24

Other

Other9th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE ISSNIP 2014
CountrySingapore
CitySingapore
Period14/4/2114/4/24

Fingerprint

Feature extraction
Classifiers
Genetic algorithms
Set theory
Labels

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems

Cite this

Sachnev, V., & Kim, H. J. (2014). Binary Coded Genetic Algorithm with Ensemble Classifier for feature selection in JPEG steganalysis. In IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings [6827700] IEEE Computer Society. https://doi.org/10.1109/ISSNIP.2014.6827700

Binary Coded Genetic Algorithm with Ensemble Classifier for feature selection in JPEG steganalysis. / Sachnev, Vasily; Kim, Hyong Joong.

IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings. IEEE Computer Society, 2014. 6827700.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sachnev, V & Kim, HJ 2014, Binary Coded Genetic Algorithm with Ensemble Classifier for feature selection in JPEG steganalysis. in IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings., 6827700, IEEE Computer Society, 9th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE ISSNIP 2014, Singapore, Singapore, 14/4/21. https://doi.org/10.1109/ISSNIP.2014.6827700
Sachnev V, Kim HJ. Binary Coded Genetic Algorithm with Ensemble Classifier for feature selection in JPEG steganalysis. In IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings. IEEE Computer Society. 2014. 6827700 https://doi.org/10.1109/ISSNIP.2014.6827700
Sachnev, Vasily ; Kim, Hyong Joong. / Binary Coded Genetic Algorithm with Ensemble Classifier for feature selection in JPEG steganalysis. IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings. IEEE Computer Society, 2014.
@inproceedings{e29621c3f86e45639861adfbb1c84afa,
title = "Binary Coded Genetic Algorithm with Ensemble Classifier for feature selection in JPEG steganalysis",
abstract = "In this paper, we propose a Binary Coded Genetic Algorithm with Ensemble Classification feature selection procedure designed for steganalysis. Proposed feature selection method was used for searching the most appropriate subset of features from 22510 dimension feature space superior for JPEG steganal-ysis. Reduced set of features shows better classification accuracy for JPEG steganalysis compared to complete set of features. In our method we used an ensemble classifier to approximate the functional relationship between the reduced feature set and class label. Search for optimal subset of features requires to solve two optimization problems: define the optimal number of features and define the optimal subset itself. Proposed Binary Coded Genetic algorithm enables to solve two optimization problems together. Each feature is coded as a binary coefficient in a binary string, which represent one solution of the feature selection problem. Genetic operations executed for binary strings (parents) results new binary strings (child) with good chance to have higher classification accuracy for JPEG steganalysis. Experimental results clearly indicate the advantage of using the proposed reduced set of features for JPEG steganalysis.",
keywords = "Extreme learning machine, JPEG steganography, Steganalysis, Undetectable data hiding",
author = "Vasily Sachnev and Kim, {Hyong Joong}",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/ISSNIP.2014.6827700",
language = "English",
isbn = "9781479928439",
booktitle = "IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Binary Coded Genetic Algorithm with Ensemble Classifier for feature selection in JPEG steganalysis

AU - Sachnev, Vasily

AU - Kim, Hyong Joong

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper, we propose a Binary Coded Genetic Algorithm with Ensemble Classification feature selection procedure designed for steganalysis. Proposed feature selection method was used for searching the most appropriate subset of features from 22510 dimension feature space superior for JPEG steganal-ysis. Reduced set of features shows better classification accuracy for JPEG steganalysis compared to complete set of features. In our method we used an ensemble classifier to approximate the functional relationship between the reduced feature set and class label. Search for optimal subset of features requires to solve two optimization problems: define the optimal number of features and define the optimal subset itself. Proposed Binary Coded Genetic algorithm enables to solve two optimization problems together. Each feature is coded as a binary coefficient in a binary string, which represent one solution of the feature selection problem. Genetic operations executed for binary strings (parents) results new binary strings (child) with good chance to have higher classification accuracy for JPEG steganalysis. Experimental results clearly indicate the advantage of using the proposed reduced set of features for JPEG steganalysis.

AB - In this paper, we propose a Binary Coded Genetic Algorithm with Ensemble Classification feature selection procedure designed for steganalysis. Proposed feature selection method was used for searching the most appropriate subset of features from 22510 dimension feature space superior for JPEG steganal-ysis. Reduced set of features shows better classification accuracy for JPEG steganalysis compared to complete set of features. In our method we used an ensemble classifier to approximate the functional relationship between the reduced feature set and class label. Search for optimal subset of features requires to solve two optimization problems: define the optimal number of features and define the optimal subset itself. Proposed Binary Coded Genetic algorithm enables to solve two optimization problems together. Each feature is coded as a binary coefficient in a binary string, which represent one solution of the feature selection problem. Genetic operations executed for binary strings (parents) results new binary strings (child) with good chance to have higher classification accuracy for JPEG steganalysis. Experimental results clearly indicate the advantage of using the proposed reduced set of features for JPEG steganalysis.

KW - Extreme learning machine

KW - JPEG steganography

KW - Steganalysis

KW - Undetectable data hiding

UR - http://www.scopus.com/inward/record.url?scp=84903725784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903725784&partnerID=8YFLogxK

U2 - 10.1109/ISSNIP.2014.6827700

DO - 10.1109/ISSNIP.2014.6827700

M3 - Conference contribution

AN - SCOPUS:84903725784

SN - 9781479928439

BT - IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings

PB - IEEE Computer Society

ER -