Scholarlink

<p>Although image steganography advances considerably in recent years, it continues to face numerous challenges. Image steganography is the practice of preserving privacy by embedding hidden information text, video, or images within a cover image to protect from human eye. This research presents a streamlined Convolutional Neural Networks (CNN) based model designed to embed a concealed image inside a cover image and retrieve the hidden image from the input. The proposed approach helps in embedding and retrieving hidden information leveraging the Encoder-Decoder technique using CNN. It spreads and compresses the information of the hidden image throughout all available bits, in contrast to conventional steganographic techniques which employ the least significant bits of the container image to conceal the majority of the message. Furthermore, the proposed approach is assessed with various metrics such as structured similarity index measurement (SSIM) and peak signal-to-noise ratio (PSNR) where empirical results show that the proposed method reported better PSNR (44.37) and SSIM (0.9956) than existing deep learning based steganographic methods and provides enhanced imperceptibility, security, robustness, and hiding capacity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel block based preparation network using convolutional neural networks for image steganography and robust data protection

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月28日

查看全文
  • Aditya Dabhade,
  • Soumendu Chakraborty,
  • Snigdha Sen

摘要

Although image steganography advances considerably in recent years, it continues to face numerous challenges. Image steganography is the practice of preserving privacy by embedding hidden information text, video, or images within a cover image to protect from human eye. This research presents a streamlined Convolutional Neural Networks (CNN) based model designed to embed a concealed image inside a cover image and retrieve the hidden image from the input. The proposed approach helps in embedding and retrieving hidden information leveraging the Encoder-Decoder technique using CNN. It spreads and compresses the information of the hidden image throughout all available bits, in contrast to conventional steganographic techniques which employ the least significant bits of the container image to conceal the majority of the message. Furthermore, the proposed approach is assessed with various metrics such as structured similarity index measurement (SSIM) and peak signal-to-noise ratio (PSNR) where empirical results show that the proposed method reported better PSNR (44.37) and SSIM (0.9956) than existing deep learning based steganographic methods and provides enhanced imperceptibility, security, robustness, and hiding capacity.