JPEG Image Steganalysis from Imbalanced Data

Jia FU; Guorui FENG; Yanli REN

doi:10.1587/transfun.E100.A.2518

JPEG Image Steganalysis from Imbalanced Data

Jia FU, Guorui FENG, Yanli REN

Full Text Views

0

Share
Cite this

Summary :

Image steganalysis can determine whether the image contains the secret messages. In practice, the number of the cover images is far greater than that of the secret images, so it is very important to solve the detection problem in imbalanced image sets. Currently, SMOTE, Borderline-SMOTE and ADASYN are three importantly synthesized algorithms used to solve the imbalanced problem. In these methods, the new sampling point is synthesized based on the minority class samples. But this research is seldom seen in image steganalysis. In this paper, we find that the features of the majority class sample are similar to those of the minority class sample based on the distribution of the image features in steganalysis. So the majority and minority class samples are both used to integrate the new sample points. In experiments, compared with SMOTE, Borderline-SMOTE and ADASYN, this approach improves detection accuracy using the FLD ensemble classifier.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E100-A No.11 pp.2518-2521

Publication Date: 2017/11/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E100.A.2518

Type of Manuscript: LETTER

Category: Information Theory

Authors

Jia FU
  School of Communication and Information Engineering, Shanghai University
Guorui FENG
  School of Communication and Information Engineering, Shanghai University
Yanli REN
  School of Communication and Information Engineering, Shanghai University

Keyword

steganalysis, JPEG images, imbalanced data, feature distribution

Cite this

Copy

Jia FU, Guorui FENG, Yanli REN, "JPEG Image Steganalysis from Imbalanced Data" in IEICE TRANSACTIONS on Fundamentals, vol. E100-A, no. 11, pp. 2518-2521, November 2017, doi: 10.1587/transfun.E100.A.2518.
Abstract: Image steganalysis can determine whether the image contains the secret messages. In practice, the number of the cover images is far greater than that of the secret images, so it is very important to solve the detection problem in imbalanced image sets. Currently, SMOTE, Borderline-SMOTE and ADASYN are three importantly synthesized algorithms used to solve the imbalanced problem. In these methods, the new sampling point is synthesized based on the minority class samples. But this research is seldom seen in image steganalysis. In this paper, we find that the features of the majority class sample are similar to those of the minority class sample based on the distribution of the image features in steganalysis. So the majority and minority class samples are both used to integrate the new sample points. In experiments, compared with SMOTE, Borderline-SMOTE and ADASYN, this approach improves detection accuracy using the FLD ensemble classifier.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E100.A.2518/_p

Copy

@ARTICLE{e100-a_11_2518,
author={Jia FU, Guorui FENG, Yanli REN, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={JPEG Image Steganalysis from Imbalanced Data},
year={2017},
volume={E100-A},
number={11},
pages={2518-2521},
abstract={Image steganalysis can determine whether the image contains the secret messages. In practice, the number of the cover images is far greater than that of the secret images, so it is very important to solve the detection problem in imbalanced image sets. Currently, SMOTE, Borderline-SMOTE and ADASYN are three importantly synthesized algorithms used to solve the imbalanced problem. In these methods, the new sampling point is synthesized based on the minority class samples. But this research is seldom seen in image steganalysis. In this paper, we find that the features of the majority class sample are similar to those of the minority class sample based on the distribution of the image features in steganalysis. So the majority and minority class samples are both used to integrate the new sample points. In experiments, compared with SMOTE, Borderline-SMOTE and ADASYN, this approach improves detection accuracy using the FLD ensemble classifier.},
keywords={},
doi={10.1587/transfun.E100.A.2518},
ISSN={1745-1337},
month={November},}

Copy

TY - JOUR
TI - JPEG Image Steganalysis from Imbalanced Data
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2518
EP - 2521
AU - Jia FU
AU - Guorui FENG
AU - Yanli REN
PY - 2017
DO - 10.1587/transfun.E100.A.2518
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E100-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2017
AB - Image steganalysis can determine whether the image contains the secret messages. In practice, the number of the cover images is far greater than that of the secret images, so it is very important to solve the detection problem in imbalanced image sets. Currently, SMOTE, Borderline-SMOTE and ADASYN are three importantly synthesized algorithms used to solve the imbalanced problem. In these methods, the new sampling point is synthesized based on the minority class samples. But this research is seldom seen in image steganalysis. In this paper, we find that the features of the majority class sample are similar to those of the minority class sample based on the distribution of the image features in steganalysis. So the majority and minority class samples are both used to integrate the new sample points. In experiments, compared with SMOTE, Borderline-SMOTE and ADASYN, this approach improves detection accuracy using the FLD ensemble classifier.
ER -