Deep Steganography using CNN and Machine Learning Techniques

Mr. Ved Rajdeep; Asst. Prof. Nimesh Vaidya; Dr. Vijaykumar B Gadhavi

doi:10.71097/IJSAT.v16.i2.5074

Deep Steganography using CNN and Machine Learning Techniques

Author(s)	Mr. Ved Rajdeep, Asst. Prof. Nimesh Vaidya, Dr. Vijaykumar B Gadhavi
Country	India
Abstract	This paper will seek to look at steganography where techniques to be embraced will use images in bid to encase secret data within other files that appear harmless. The largest motivation will come from steganography’s novelty feature and high security which would also safeguard information from future intruders. Thus, a complex deep steganography model will be Developed by implementing the Machine Learning and Steganography approaches. The purpose of the model will be to embed one image into another in order that cannot easily be distinguished and at the same time the quality of the images will not be distorted greatly. As such, the main objective of this study will be to optimise the Editors’ ability to balance the potential of information embedding with the image quality in order to address current challenges in the field of information security. With the help of solution with machine learning methods, the model will be able to change the payload depending on the characteristics of the cover image. This will enhance the fortification of the model guarding temporary sensitive data in the digital terrain by strengthening and diversifying it. The outcome of this research will therefore be a highly developed deep steganography model that will be integrated to specifically hide and extract images undetectably. The model will be trained by CNNs and RNNs, respectively, in an iteratively fashion. Specific loss functions will be employed in order to prevent excessive distortion of the cover pictures and to optimize the ability to hide data. The results will be analyzed and discussed in terms of quantitative measures including PSNR, SSIM and the message recovery rate and general visual inspections. The additional validations, such as the robustness tests, computational efficiency assessments, and the security tests will increase confidence in the model’s performance as well as in its reliability. Consequently, the deep steganography model presented in this paper will utilize modern forms of learning as well as steganographic skills to form a considerable strategy in concealing and recovering sensitive data in images. The sequential process of establishing and testing the model will demonstrate its applicability for use in safeguarding digital information in an increasingly integrated global environment.
Keywords	Deep Steganography, Convolutional Neural, Networks (CNNs), Image Embedding, Information Security, Machine Learning
Field	Engineering
Published In	Volume 16, Issue 2, April-June 2025
Published On	2025-05-12
DOI	https://doi.org/10.71097/IJSAT.v16.i2.5074
Short DOI	https://doi.org/g9kc54

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 4 Cover Page Vol 15 Isu 3 Cover Page Vol 15 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Deep Steganography using CNN and Machine Learning Techniques

Share this