Introducing a Novel Approach to Concealing Textual Information Within Digital Images Through the Use of Neural Networks

Document Type : Research Paper

Authors

1 Department of Electrical Engineering, Faculty of Electrical Engineering, Qazvin branch, Islamic Azad University, Qazvin, Iran.

2 . Department of Electrical Engineering, Faculty of Electrical Engineering, University of Mississippi, USA.

3 Department of Electrical Engineering, Faculty of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran.

Abstract

In steganography, a text is placed in a digital image in a secure, imperceptible and retrievable way. The three main methods of digital image steganography are spatial methods, transformation and neural network. Spatial methods change the pixel values of an image to embed information, while transform methods embed information hidden in the frequency of the image.
Neural networks are use to perform the hiding process  and it is the main part of this research. This research examines the use of LSTM[1] deep neural networks in digital image text steganography. This work extends an existing implementation that uses a two-dimensional LSTM to perform the preparation, hiding, and extraction steps of the steganography process. The proposed method modified the structure of  LSTM and used a gain function based on several image similarity measures to maximize the indiscernibility between an overlay and a steganographic image. Genetic algorithm helps in improving the structure of LSTM networks in the textual information within hidden images, with optimizations (number of layers, neurons, evaluations) and selection of appropriate features, increasing the accuracy, improving image quality and preventing overfitting. This method helps to find the optimal architecture for the LSTM network and improves the efficiency of the steganography.
The proposed method demonstrates superior performance based on three evaluation metrics Peak Signal-to-Noise Ratio (PSNR[2]) in decibels, Mean Squared Error (MSE[3]), and accuracy rate in percentage compared to three other benchmark images (lena.png, peppers.png, mandril.png, and monkey.png), achieving values of 93.665275 dB, 0.6945 MSE, and 97.23% accuracy, respectively. The proposed method modified the structure of  LSTM and used a gain function.

Keywords

Main Subjects

References

[1] P. N. Shingote, A. Bhujbal, P. M. Syed, Advanced Security Usin Cryptographyand LSBMatching Steganography, IJCER, 3(2), 52-55,  2014
[2] F. G. Mohammadi, M. S. Abadeh, Image steganalysis using a bee colony based feature selection algorithm., Engineering Applications of Artificial Intelligence, 2014
[3] Z. V. Patel, S. A. Gadhiya,.A Survey Paper on Steganography and Cryptography, International Multidisciplinary Research Journal (RHIMRJ), Volume-2, Issue-5.  2015
[4] Y. Wang, X. Liu, Z. Gao, “Chaos‑Based Image Steganography,” IEEE Internet Things J., vol. 10, no. 2, pp. 1478–1487, 2023.
[5] M. Juneja, P. S. Sandhu, Improved LSB based Steganography Techniques for ColorImages in Spatial Domain. IJ Network Security, 16(4),366376, 2014
[6] Y. Wang et al., “Chaos‑Based Image Steganography,” IEEE IoT J., 2023.
[7] R. C. Gonzalez, R. E. Woods, Digital Image Processing translator: Ainullah Jafarnjad Qomi, publisher: Computer Science Publications, 4th edition, 2021
[8] H. Sajedi and Sh. R. Yaghoubi, “Review on Steganographic Methods in Texts”, 2018.
[9] D. Gomez, R. Martinez, J. Lopez, “LSTM‑Assisted Data Hiding in Color Images,” IEEE Access, vol. 10, pp. 109123–109135, 2022.
[10] S. M Hosseininia, A. Nemati, Investigation of image-based information encryption methods with the approach of increasing the security of information and communications against multiple attacks, Specialized Scientific Quarterly of New Technologies in Electrical and Computer Engineering, Volume 3, Number 4, 2022[11] T. Nguyen, P. Tran, H. Huynh, “Deep LSTM‑Based Image Steganography,” IEEE Access, vol. 9, pp. 87632–87645, 2021.
[12] N. Patel, M. Patel, K. Joshi, “Robust Steganographic System Using Autoencoders,” IEEE Trans. Inf. Forensics Secur., vol. 18, pp. 220–233, 2022.
 [13] A. Sabhany, A. Ahmed, H. Ali, R. Mokhtar, “Digital audio steganography: Systematic review,” classification, and analysis of the current state of the art. Computer Science Review, Volume 38, November 2020
[14] D. Wenbo, Z. Mingyuan, Y. Wen, P. Matjaž, W. Dapeng. “The networked evolutionary algorithm: A network science perspective” , Applied Mathematics and Computation, Volume 338, Pages 33-43. 1 December 2018
[15] E. Asadzadeh, M. Asadzadeh, M. Asadbek Genetic Algorithm, the First Publications, 2018[16]  A. R. Mirqadari and A. Jolfaei, "A new scheme for image encryption using chaotic mappings," Modern Defense Sciences and Technologies (Non-Agent Defense Sciences and Technologies), vol. 2, no. 2 (series 4), pp. 111-124, 2019 

Files

History

  • Receive Date: 30 December 2024
  • Revise Date: 16 April 2025
  • Accept Date: 17 September 2025

Share

How to cite

Statistics