Deep Steganography using CNN and Machine Learning Techniques

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

doi:10.71097/IJSAT.v16.i2.5076

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 explores advanced steganographic techniques that leverage digital images as carriers to conceal secret information within visually benign files. The core motivation lies in steganography’s inherent capability to ensure confidentiality through invisibility, offering an innovative and secure approach to safeguarding sensitive data from potential cyber threats. To this end, a sophisticated deep steganography framework is proposed, combining machine learning with steganographic principles to enable the seamless embedding of one image within another. The design ensures that the concealed image remains indistinguishable to the human eye while preserving the overall visual integrity of the cover image. The primary objective of this research is to enhance the effectiveness of data embedding while maintaining high visual quality, addressing critical challenges in the domain of information security. Through the integration of adaptive machine learning algorithms, the model is capable of dynamically adjusting the payload size in accordance with the structural characteristics of the cover image. This adaptability reinforces the system’s robustness, making it more resilient against unauthorized detection and extraction. The proposed model employs Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) in a joint training strategy, guided by customized loss functions designed to minimize distortion and maximize embedding fidelity. The system’s performance is evaluated using objective metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and message recovery rate, supplemented by visual inspection and comprehensive robustness testing. Additional assessments of computational efficiency and resistance to steganalysis further validate the model’s reliability and applicability. Ultimately, the deep steganography system introduced in this study demonstrates the potential of modern neural network architectures in constructing secure, covert communication channels. Its development and empirical validation illustrate its practical utility in preserving data privacy and integrity across increasingly interconnected digital ecosystems..
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	2025-05-13
DOI	https://doi.org/10.71097/IJSAT.v16.i2.5076
Short DOI	https://doi.org/g9kc53

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