Home > Published Issues > 2024 > Volume 15, No. 1, 2024 >
JAIT 2024 Vol.15(1): 33-39
doi: 10.12720/jait.15.1.33-39

Preprocessing Strategy to Improve the Performance of Convolutional Neural Networks Applied to Steganalysis in the Spatial Domain

Mario Alejandro Bravo-Ortiz 1,*, Esteban Mercado-Ruiz 1, Juan Pablo Villa-Pulgarin 1,
Harold Brayan Arteaga-Arteaga 1, Gustavo Isaza 2, Raúl Ramos-Pollán 3,
Manuel Alejandro Tamayo-Monsalve 1,4, and Reinel Tabares-Soto 1,2
1. Departamento de Electrónica y Automatización, Universidad Autónoma de Manizales, Manizales, Caldas, Colombia
2. Departamento de Sistemas e Informática, Universidad de Caldas, Manizales, Caldas, Colombia
3. Departamento de Ingeniería de Sistemas, Universidad de Antioquia, Medellín, Antioquia, Colombia
4. Facultad de Ciencias e Ingeniería, Universidad de Manizales, Manizales, Caldas, Colombia
Email: mario.bravoo@autonoma.edu.co (M.A.B.O.)
*Corresponding author

Manuscript received February 14, 2023; revised March 28, 2023; accepted May 19, 2023; published January 9, 2024.

Abstract—Recent research has shown that deep learning techniques outperform traditional steganography and steganalysis methods. As a result, researchers have proposed increasingly complex and more extensive convolutional Neural Networks (CNNs) to detect Steganographic images to achieve a 1%–2% improvement over the state-of-the-art. In this paper, we propose a data preprocessing and distribution strategy that enhances accuracy and convergence during training. Our method involves bifurcating Spatial Rich Model (SRM) and Discrete Cosine Transform (DCT) filters, with one branch being trainable and the other untrainable. This strategy is followed by three blocks of residual convolutions and an excitation layer. Our proposed method improves the accuracy of CNNs applied to steganalysis by 2%–15% while maintaining stability.
Keywords—convolutional neural network, deep learning, steganalysis, steganography, steganographic filters

Cite: Mario Alejandro Bravo-Ortiz, Esteban Mercado-Ruiz, Juan Pablo Villa-Pulgarin, Harold Brayan Arteaga-Arteaga, Gustavo Isaza, Raúl Ramos-Pollán, Manuel Alejandro Tamayo-Monsalve, and Reinel Tabares-Soto, "Preprocessing Strategy to Improve the Performance of Convolutional Neural Networks Applied to Steganalysis in the Spatial Domain," Journal of Advances in Information Technology, Vol. 15, No. 1, pp. 33-39, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.