Artificial Intelligence-Based Digital Image Steganalysis

Ahmed I. Iskanderani; Ibrahim M. Mehedi; Abdulah Jeza Aljohani; Mohammad Shorfuzzaman; Farzana Akther; Thangam Palaniswamy; Shaikh Abdul Latif; Abdul Latif

doi:10.1155/2021/9923389

Artificial Intelligence-Based Digital Image Steganalysis

Ahmed I. Iskanderani, Ibrahim M. Mehedi^*, Abdulah Jeza Aljohani, Mohammad Shorfuzzaman, Farzana Akther, Thangam Palaniswamy, Shaikh Abdul Latif, Abdul Latif

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

Abstract

Recently, deep learning-based models are being extensively utilized for steganalysis. However, deep learning models suffer from overfitting and hyperparameter tuning issues. Therefore, in this paper, an efficient θ-nondominated sorting genetic algorithm-(θ NSGA-) III based densely connected convolutional neural network (DCNN) model is proposed for image steganalysis. θ NSGA-III is utilized to tune the initial parameters of DCNN model. It can control the accuracy and f-measure of the DCNN model by utilizing them as the multiobjective fitness function. Extensive experiments are drawn on STEGRT1 dataset. Comparison of the proposed model is also drawn with the competitive steganalysis model. Performance analyses reveal that the proposed model outperforms the existing steganalysis models in terms of various performance metrics.

Original language	English
Article number	9923389
Journal	Security and Communication Networks
Volume	2021
DOIs	https://doi.org/10.1155/2021/9923389
Publication status	Published - 2021
Externally published	Yes

Access to Document

10.1155/2021/9923389

Cite this

@article{c893b5f25d364f8c8eeabad4879a78a9,

title = "Artificial Intelligence-Based Digital Image Steganalysis",

abstract = "Recently, deep learning-based models are being extensively utilized for steganalysis. However, deep learning models suffer from overfitting and hyperparameter tuning issues. Therefore, in this paper, an efficient θ-nondominated sorting genetic algorithm-(θ NSGA-) III based densely connected convolutional neural network (DCNN) model is proposed for image steganalysis. θ NSGA-III is utilized to tune the initial parameters of DCNN model. It can control the accuracy and f-measure of the DCNN model by utilizing them as the multiobjective fitness function. Extensive experiments are drawn on STEGRT1 dataset. Comparison of the proposed model is also drawn with the competitive steganalysis model. Performance analyses reveal that the proposed model outperforms the existing steganalysis models in terms of various performance metrics.",

author = "Iskanderani, \{Ahmed I.\} and Mehedi, \{Ibrahim M.\} and Aljohani, \{Abdulah Jeza\} and Mohammad Shorfuzzaman and Farzana Akther and Thangam Palaniswamy and Latif, \{Shaikh Abdul\} and Abdul Latif",

note = "Publisher Copyright: {\textcopyright} 2021 Ahmed I. Iskanderani et al.",

year = "2021",

doi = "10.1155/2021/9923389",

language = "English",

volume = "2021",

journal = "Security and Communication Networks",

issn = "1939-0114",

}

TY - JOUR

T1 - Artificial Intelligence-Based Digital Image Steganalysis

AU - Iskanderani, Ahmed I.

AU - Mehedi, Ibrahim M.

AU - Aljohani, Abdulah Jeza

AU - Shorfuzzaman, Mohammad

AU - Akther, Farzana

AU - Palaniswamy, Thangam

AU - Latif, Shaikh Abdul

AU - Latif, Abdul

PY - 2021

Y1 - 2021

N2 - Recently, deep learning-based models are being extensively utilized for steganalysis. However, deep learning models suffer from overfitting and hyperparameter tuning issues. Therefore, in this paper, an efficient θ-nondominated sorting genetic algorithm-(θ NSGA-) III based densely connected convolutional neural network (DCNN) model is proposed for image steganalysis. θ NSGA-III is utilized to tune the initial parameters of DCNN model. It can control the accuracy and f-measure of the DCNN model by utilizing them as the multiobjective fitness function. Extensive experiments are drawn on STEGRT1 dataset. Comparison of the proposed model is also drawn with the competitive steganalysis model. Performance analyses reveal that the proposed model outperforms the existing steganalysis models in terms of various performance metrics.

AB - Recently, deep learning-based models are being extensively utilized for steganalysis. However, deep learning models suffer from overfitting and hyperparameter tuning issues. Therefore, in this paper, an efficient θ-nondominated sorting genetic algorithm-(θ NSGA-) III based densely connected convolutional neural network (DCNN) model is proposed for image steganalysis. θ NSGA-III is utilized to tune the initial parameters of DCNN model. It can control the accuracy and f-measure of the DCNN model by utilizing them as the multiobjective fitness function. Extensive experiments are drawn on STEGRT1 dataset. Comparison of the proposed model is also drawn with the competitive steganalysis model. Performance analyses reveal that the proposed model outperforms the existing steganalysis models in terms of various performance metrics.

UR - https://www.scopus.com/pages/publications/85105396928

U2 - 10.1155/2021/9923389

DO - 10.1155/2021/9923389

M3 - Article

AN - SCOPUS:85105396928

SN - 1939-0114

VL - 2021

JO - Security and Communication Networks

JF - Security and Communication Networks

M1 - 9923389

ER -

Artificial Intelligence-Based Digital Image Steganalysis

Abstract

Access to Document

Other files and links

Fingerprint

Cite this