CNN - Powered Deep Learning Framework for Advanced Image Steganography and Data Security

Image steganography, the art of concealing information within images, has advanced significantly with the integration of deep learning, enhancing both data security and concealment. In this study, we propose a novel framework leveraging Convolutional Neural Networks (CNNs) to embed and extract hidden messages seamlessly. Our approach trains a CNN to learn robust feature representations that enable imperceptible integration of concealed data with cover images, ensuring high resistance to human detection and steganalysis. Extensive evaluation on a dataset demonstrates the superiority of our method in payload capacity, image quality, and security compared to traditional steganography techniques. These findings underscore the transformative potential of deep learning-based steganography for secure communication and data protection in the digital age.

Authors

Publication Details

Published
2025-03-04
DOI
https://doi.org/10.1109/icvadv63329.2025.10961912
Citations
1
Primary Topic
Digital Media Forensic Detection
Type
article
Field-Weighted Citation Impact
1.28
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

CNN - Powered Deep Learning Framework for Advanced Image Steganography and Data Security

Shahab Pasha, N. Harish, K. Ajay, S. Sreenu
1 citations
Digital Media Forensic Detection
1.28
article

CNN - Powered Deep Learning Framework for Advanced Image Steganography and Data Security

Shahab Pasha, N. Harish, K. Ajay, S. Sreenu
article en
1 citations

Abstract

Image steganography, the art of concealing information within images, has advanced significantly with the integration of deep learning, enhancing both data security and concealment. In this study, we propose a novel framework leveraging Convolutional Neural Networks (CNNs) to embed and extract hidden messages seamlessly. Our approach trains a CNN to learn robust feature representations that enable imperceptible integration of concealed data with cover images, ensuring high resistance to human detection and steganalysis. Extensive evaluation on a dataset demonstrates the superiority of our method in payload capacity, image quality, and security compared to traditional steganography techniques. These findings underscore the transformative potential of deep learning-based steganography for secure communication and data protection in the digital age.

Openalex Percentile: Top 21%
Digital Media Forensic Detection
1.28
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.