Scholarlink

<p>This paper proposes a deep steganography framework using a three-layered Convolutional Neural Network (CNN) architecture—preparation, hiding, and revealing networks—for robust data hiding. The preparation network employs 50, 10, and 5 filters (3<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation>3, 4<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation>4, 5<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation>5) for edge feature extraction, followed by adaptive embedding in the hiding network. Optimized with four loss functions, Loss Function 3 (LF 3), integrating mean and variance terms, achieves a payload of 3–5 bits per pixel and improved PSNR across Tiny-ImageNet, Linnaeus 5 dataset, Sky-text dataset and RGB-BMP datasets. LF 3 ensures robustness against Gaussian noise, cropping, and rotation, with low detection rates in histogram, statistical, and CNN-based steganalysis. Compared to state-of-the-art Generative Adversarial Network (GAN) based methods, LF 3 offers higher payload-robustness balance and computational efficiency, advancing secure data hiding for applications like medical imaging.</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

Deep steganographic approach for reliable data hiding using convolutional neural networks and adaptive loss optimization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月23日

查看全文
  • Malathi P.,
  • Gireesh Kumar T.

摘要

This paper proposes a deep steganography framework using a three-layered Convolutional Neural Network (CNN) architecture—preparation, hiding, and revealing networks—for robust data hiding. The preparation network employs 50, 10, and 5 filters (3 \(\times\) 3, 4 \(\times\) 4, 5 \(\times\) 5) for edge feature extraction, followed by adaptive embedding in the hiding network. Optimized with four loss functions, Loss Function 3 (LF 3), integrating mean and variance terms, achieves a payload of 3–5 bits per pixel and improved PSNR across Tiny-ImageNet, Linnaeus 5 dataset, Sky-text dataset and RGB-BMP datasets. LF 3 ensures robustness against Gaussian noise, cropping, and rotation, with low detection rates in histogram, statistical, and CNN-based steganalysis. Compared to state-of-the-art Generative Adversarial Network (GAN) based methods, LF 3 offers higher payload-robustness balance and computational efficiency, advancing secure data hiding for applications like medical imaging.