# Deep Learning for Predictive Analytics in Reversible Steganography

arXiv: https://arxiv.org/abs/2106.06924 · HTML: https://mlsanity.com/paper/2106.06924/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 75 references that are in the map.
- First posted on arXiv 13 Jun 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization](https://mlsanity.com/paper/1708.08689/) (2017)
- [Residual Dense Network for Image Restoration](https://mlsanity.com/paper/1812.10477/) (2018)
- [Deep Learning for Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/1808.03344/) (2018)
- [Distortion Agnostic Deep Watermarking](https://mlsanity.com/paper/2001.04580/) (2020)
- [Generating Steganographic Images via Adversarial Training](https://mlsanity.com/paper/1703.00371/) (2017)
- [CNN Based Adversarial Embedding with Minimum Alteration for Image Steganography](https://mlsanity.com/paper/1803.09043/) (2018)
- [Steganographic Generative Adversarial Networks](https://mlsanity.com/paper/1703.05502/) (2017)
- [Generative Reversible Data Hiding by Image to Image Translation via GANs](https://mlsanity.com/paper/1905.02872/) (2019)

## Built on by (most cited first, 1 of 1)

- [Bayesian Neural Networks for Reversible Steganography](https://mlsanity.com/paper/2201.02478/) (2022)

## Abstract (arXiv)

Deep learning is regarded as a promising solution for reversible steganography. There is an accelerating trend of representing a reversible steo-system by monolithic neural networks, which bypass intermediate operations in traditional pipelines of reversible steganography. This end-to-end paradigm, however, suffers from imperfect reversibility. By contrast, the modular paradigm that incorporates neural networks into modules of traditional pipelines can stably guarantee reversibility with mathematical explainability. Prediction-error modulation is a well-established reversible steganography pipeline for digital images. It consists of a predictive analytics module and a reversible coding module. Given that reversibility is governed independently by the coding module, we narrow our focus to the incorporation of neural networks into the analytics module, which serves the purpose of predicting pixel intensities and a pivotal role in determining capacity and imperceptibility. The objective of this study is to evaluate the impacts of different training configurations upon predictive accuracy of neural networks and provide practical insights. In particular, we investigate how different initialisation strategies for input images may affect the learning process and how different training strategies for dual-layer prediction respond to the problem of distributional shift. Furthermore, we compare steganographic performance of various model architectures with different loss functions.