GAN-Based Encoding Model for Reversible Image Steganography

Kuyoro, Afolashade; Nzenwata, Uchenna J.; Awodele, Olufunsho; Idowu, Sunday

doi:10.18280/ria.360407

Cited by 5 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of neural networks and associated technologies allows us today to have powerful algorithms for deep learning allowing SISR in an efficient way with better performances thanks to the technological development offering several architectures like CNN [29], GAN [30,31], and others (Table 1); as well as many adapted loss functions [32].…”

Section: Hr=sr(lrf)mentioning

confidence: 99%

Study of Deep Learning-based models for Single Image Super-Resolution

Soufi¹,

Belouadha²

2022

RIA

View full text Add to dashboard Cite

The super-resolution of images has seen remarkable progress, especially with the use of deep learning models. This technique allows having a better-quality image from one or more low-resolution versions. Super-resolution, therefore, aims at enriching a lowresolution image with additional pixel density and high-frequency detail. This paper presents a comprehensive empirical study based on a systematic review of deep learningbased models for single image super-resolution (SISR), exploring the set of techniques offered by deep learning technology and used for SISR. In this paper, we present a global and complete state of the art on deep learning model based on reference metrics (mainly Peak Signal to Noise Ratio -PSNR-and Structural SIMilarity -SSIM-) in the field of computer visualization and image reconstruction. This study was done on several deep learning designs with 90 different models tested on 7 reference datasets in the computer vision domain. Thus, our goal is to present a benchmark to demonstrate the performance and limitations of these models as well as to guide future research in the field of super image resolution to develop efficient algorithms. Moreover, our study covers different neural network architectures (Generative Adversarial Networks -GAN-, Convolutional Neural Networks -CNN-, and Recurrent Neural Networks -RNN-...), using different techniques and technologies.

show abstract

Section: Hr=sr(lrf)mentioning

confidence: 99%

Study of Deep Learning-based models for Single Image Super-Resolution

Soufi¹,

Belouadha²

2022

RIA

View full text Add to dashboard Cite

show abstract

“…Analogously, text and audio files have also been utilised to harbour concealed data. To the unassuming observer, such text or audio manifests as entirely innocuous [14][15][16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

“…A representation of the steganographic data model, as depicted in Figure 1, comprises the covering image, the covert message, the steganographic data method, and the resultant stego image [14][15][16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Enhanced Efficiency and Security in LSB2 Steganography: Burst Embedding and Private Key Integration

Rasras,

Sara,

Alqadi

2023

View full text Add to dashboard Cite

In the realm of digital colour image steganography, the utilisation of an image key for the extraction of essential covering stego-bytes from predetermined secret positions was explored. The traditional Least Significant Bit (LSB) and LSB2 methodologies were streamlined by substituting the logical operations within both the hiding and extraction functions with straightforward assignment operations. An enhancement was introduced to the LSB2 steganographic methods for secret message conveyance without compromising data hiding capacity. Instead of the conventional character-by-character embedding seen in the LSB2 method, the binary code of the concealed message was embedded in a burst manner within the covering image. Similarly, the extraction from the stego image was conducted in a burst fashion, leading to a reduction in the processes required for both data hiding and extraction. As a result, shorter hiding and extraction durations were achieved, culminating in augmented data steganography throughput. For bolstering message security against potential breaches, the proposed ULSB2 method integrated a confidential private key (PK) composed of two double values. This key provisioned the necessary key space to deter hacking endeavours. A comparative analysis was conducted between the outcomes derived from the ULSB2 method and those of prevailing techniques to delineate the enhancements in both quality and speed of message steganography.

show abstract