# WISERNet: Wider Separate-then-reunion Network for Steganalysis of Color Images

arXiv: https://arxiv.org/abs/1803.04805 · HTML: https://mlsanity.com/paper/1803.04805/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2018.

## Built on by (most cited first, 8 of 8)

- [Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization](https://mlsanity.com/paper/2107.02434/) (2021)
- [Deep Learning for Steganalysis of Diverse Data Types: A review of methods, taxonomy, challenges and future directions](https://mlsanity.com/paper/2308.04522/) (2023)
- [A Brief Survey on Deep Learning Based Data Hiding](https://mlsanity.com/paper/2103.01607/) (2021)
- [Universal Deep Network for Steganalysis of Color Image based on Channel Representation](https://mlsanity.com/paper/2111.12231/) (2021)
- [STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor Decomposition](https://mlsanity.com/paper/2206.05651/) (2022)
- [Incorporating Ensemble and Transfer Learning For An End-To-End Auto-Colorized Image Detection Model](https://mlsanity.com/paper/2309.14478/) (2023)
- [Natias: Neuron Attribution based Transferable Image Adversarial Steganography](https://mlsanity.com/paper/2409.04968/) (2024)
- [Rethinking Security of Diffusion-based Generative Steganography](https://mlsanity.com/paper/2602.10219/) (2026)

## Abstract (arXiv)

Until recently, deep steganalyzers in spatial domain have been all designed for gray-scale images. In this paper, we propose WISERNet (the wider separate-then-reunion network) for steganalysis of color images. We provide theoretical rationale to claim that the summation in normal convolution is one sort of "linear collusion attack" which reserves strong correlated patterns while impairs uncorrelated noises. Therefore in the bottom convolutional layer which aims at suppressing correlated image contents, we adopt separate channel-wise convolution without summation instead. Conversely, in the upper convolutional layers we believe that the summation in normal convolution is beneficial. Therefore we adopt united normal convolution in those layers and make them remarkably wider to reinforce the effect of "linear collusion attack". As a result, our proposed wide-and-shallow, separate-then-reunion network structure is specifically suitable for color image steganalysis. We have conducted extensive experiments on color image datasets generated from BOSSBase raw images and another large-scale dataset which contains 100,000 raw images, with different demosaicking algorithms and down-sampling algorithms. The experimental results show that our proposed network outperforms other state-of-the-art color image steganalytic models either hand-crafted or learned using deep networks in the literature by a clear margin. Specifically, it is noted that the detection performance gain is achieved with less than half the complexity compared to the most advanced deep-learning steganalyzer as far as we know, which is scarce in the literature.