Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models

As machine learning continues to evolve, traditional image steganography techniques find themselves increasingly unable to meet the dual challenge of deceiving both the human visual system and machine learning models. In response, this paper introduces the Visually Robust Image Steganography (VRIS)...

Full description

Saved in:
Bibliographic Details
Main Authors: Fan Zhang, Yanhua Dong, Hongyu Sun
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/22/10458
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850149895066877952
author Fan Zhang
Yanhua Dong
Hongyu Sun
author_facet Fan Zhang
Yanhua Dong
Hongyu Sun
author_sort Fan Zhang
collection DOAJ
description As machine learning continues to evolve, traditional image steganography techniques find themselves increasingly unable to meet the dual challenge of deceiving both the human visual system and machine learning models. In response, this paper introduces the Visually Robust Image Steganography (VRIS) model, specifically tailored for this dual deception task. The VRIS model elevates visual security through the use of specialized feature extraction and processing methodologies. It meticulously conducts feature-level fusion between secret images and cover images, ensuring a high level of visual similarity between them. To effectively mislead machine learning models, the VRIS model incorporates a sophisticated strategy utilizing random noise factors and discriminators. This involves adding controlled amounts of random Gaussian noise to the encrypted image, thereby enhancing the difficulty for machine learning frameworks to recognize it. Furthermore, the discriminator is trained to discern between the noise-infused encrypted image and the original cover image. Through adversarial training, the discriminator and VRIS model refine each other, successfully deceiving the machine learning systems. Additionally, the VRIS model presents an innovative method for extracting and reconstructing secret images. This approach safeguards secret information from unauthorized access while enabling legitimate users to non-destructively extract and reconstruct images by leveraging multi-scale features from the encrypted image, combined with advanced feature fusion and reconstruction techniques. Experimental results validate the effectiveness of the VRIS model, achieving high PSNR and SSIM scores on the LFW dataset and demonstrating significant deception capabilities against the ResNet50 model on the Mini-ImageNet dataset, with an impressive misclassification rate of 99.24%.
format Article
id doaj-art-ef2a13faef1d49ad96115173cd7671ba
institution OA Journals
issn 2076-3417
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-ef2a13faef1d49ad96115173cd7671ba2025-08-20T02:26:45ZengMDPI AGApplied Sciences2076-34172024-11-0114221045810.3390/app142210458Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning ModelsFan Zhang0Yanhua Dong1Hongyu Sun2College of Mathematics and Computer, Jilin Normal University, Siping 136000, ChinaCollege of Mathematics and Computer, Jilin Normal University, Siping 136000, ChinaCollege of Mathematics and Computer, Jilin Normal University, Siping 136000, ChinaAs machine learning continues to evolve, traditional image steganography techniques find themselves increasingly unable to meet the dual challenge of deceiving both the human visual system and machine learning models. In response, this paper introduces the Visually Robust Image Steganography (VRIS) model, specifically tailored for this dual deception task. The VRIS model elevates visual security through the use of specialized feature extraction and processing methodologies. It meticulously conducts feature-level fusion between secret images and cover images, ensuring a high level of visual similarity between them. To effectively mislead machine learning models, the VRIS model incorporates a sophisticated strategy utilizing random noise factors and discriminators. This involves adding controlled amounts of random Gaussian noise to the encrypted image, thereby enhancing the difficulty for machine learning frameworks to recognize it. Furthermore, the discriminator is trained to discern between the noise-infused encrypted image and the original cover image. Through adversarial training, the discriminator and VRIS model refine each other, successfully deceiving the machine learning systems. Additionally, the VRIS model presents an innovative method for extracting and reconstructing secret images. This approach safeguards secret information from unauthorized access while enabling legitimate users to non-destructively extract and reconstruct images by leveraging multi-scale features from the encrypted image, combined with advanced feature fusion and reconstruction techniques. Experimental results validate the effectiveness of the VRIS model, achieving high PSNR and SSIM scores on the LFW dataset and demonstrating significant deception capabilities against the ResNet50 model on the Mini-ImageNet dataset, with an impressive misclassification rate of 99.24%.https://www.mdpi.com/2076-3417/14/22/10458image steganographydual deceptionfeature-level fusionrandom noise factoradversarial training
spellingShingle Fan Zhang
Yanhua Dong
Hongyu Sun
Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models
Applied Sciences
image steganography
dual deception
feature-level fusion
random noise factor
adversarial training
title Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models
title_full Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models
title_fullStr Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models
title_full_unstemmed Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models
title_short Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models
title_sort research on key technologies of image steganography based on simultaneous deception of vision and deep learning models
topic image steganography
dual deception
feature-level fusion
random noise factor
adversarial training
url https://www.mdpi.com/2076-3417/14/22/10458
work_keys_str_mv AT fanzhang researchonkeytechnologiesofimagesteganographybasedonsimultaneousdeceptionofvisionanddeeplearningmodels
AT yanhuadong researchonkeytechnologiesofimagesteganographybasedonsimultaneousdeceptionofvisionanddeeplearningmodels
AT hongyusun researchonkeytechnologiesofimagesteganographybasedonsimultaneousdeceptionofvisionanddeeplearningmodels