Proceedings Article10.23919/indiacom54597.2022.9763273
Multi-data Image Steganography using Generative Adversarial Networks
23 Mar 2022
4
TL;DR: In this paper , a multi-data deep learning steganography model has been developed using a well known deep learning model called Generative Adversarial Networks (GAN) more specifically using deep convolutional GANs (DCGAN).
read more
Abstract: The success of deep learning based steganography has shifted focus of researchers from traditional steganography approaches to deep learning based steganography. Various deep steganographic models have been developed for improved security, capacity and invisibility. In this work a multi-data deep learning steganography model has been developed using a well known deep learning model called Generative Adversarial Networks (GAN) more specifically using deep convolutional Generative Adversarial Networks (DCGAN). The model is capable of hiding two different messages, meant for two different receivers, inside a single cover image. The proposed model consists of four networks namely Generator, Steganalyzer Extractor1 and Extractor2 network. The Generator hides two secret messages inside one cover image which are extracted using two different extractors. The Steganalyzer network differentiates between the cover and stego images generated by the generator network. The experiment has been carried out on CelebA dataset. Two commonly used distortion metrics Peak signal-to-Noise ratio (PSNR) and Structural Similarity Index Metric (SSIM) are used for measuring the distortion in the stego image The results of experimentation show that the stego images generated have good imperceptibility and high extraction rates.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A new framework for analyzing color models with generative adversarial networks for improved steganography
Bisma Sultan,M. ArifWani +1 more
TL;DR: The results show that the proposed framework improves the security of steganography even when the embedding capacity is increased, and compared with the RGB and other color models, the CIE-XYZ model produces the best results with Generative Adversarial Networks for Steganography.
8
Anti-rounding Image Steganography with Separable Fine-tuned Network
TL;DR: Wang et al. as mentioned in this paper proposed an anti-rounding image steganography method with separable fine-tuning network architecture which includes the joint training stage (JT-stage) and the separable finetuning stage (SF-stage), which effectively reduces the degradation of the image quality and steganalysis performance.
6
Steganography in Style Transfer
Ruolan Shi,Zi-wen Wang,Yunlong Hao,Xinpeng Zhang +3 more
TL;DR: Researchers propose a steganographic method that disguises data embedding as a deep neural network performing style transfer, achieving more effective and secure data concealment in style-transferred images compared to existing algorithms.
Elevating file security through advances multiple image steganography
Putta Srivani Putta Srivani
TL;DR: Steganography, the art of hiding information within other data, is the art of hiding information within other data in an age of increasing digital communication and data transfer.
References
•Proceedings Article
Hiding images in plain sight: deep steganography
Shumeet Baluja
- 04 Dec 2017
TL;DR: This study attempts to place a full size color image within another image of the same size by compressing and distributes the secret image's representation across all of the available bits of the carrier image.
Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
TL;DR: Experimental results show that the proposed automatic steganographic distortion learning framework can effectively evolve from nearly naïve random $\pm 1$ embedding at the beginning to much more advanced content-adaptive embedding which tries to embed secret bits in textural regions.
407
A Novel Image Steganography Method via Deep Convolutional Generative Adversarial Networks
TL;DR: A novel image SWE method based on deep convolutional generative adversarial networks that has the advantages of highly accurate information extraction and a strong ability to resist detection by state-of-the-art image steganalysis algorithms.
289
An Inpainting-Assisted Reversible Steganographic Scheme Using a Histogram Shifting Mechanism
TL;DR: A novel prediction-based reversible steganographic scheme based on image inpainting that provides a greater embedding rate and better visual quality compared with recently reported methods.
255
An Embedding Cost Learning Framework Using GAN
TL;DR: A distortion function generating a framework for steganography that outperforms the current state-of-the-art steganographic schemes and the adversarial training time is reduced dramatically compared with the GAN-based automatic Steganographic distortion learning framework (ASDL-GAN).
242