# Robust Spatial-spread Deep Neural Image Watermarking

arXiv: https://arxiv.org/abs/2005.11735 · HTML: https://mlsanity.com/paper/2005.11735/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2020.

## Built on by (most cited first, 6 of 6)

- [Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography](https://mlsanity.com/paper/2107.09287/) (2021)
- [A Brief Survey on Deep Learning Based Data Hiding](https://mlsanity.com/paper/2103.01607/) (2021)
- [A Brief Yet In-Depth Survey of Deep Learning-Based Image Watermarking](https://mlsanity.com/paper/2308.04603/) (2023)
- [Swap It Like Its Hot: Segmentation-based spoof attacks on eye-tracking images](https://mlsanity.com/paper/2404.13827/) (2024)
- [Robust Watermarking using Diffusion of Logo into Autoencoder Feature Maps](https://mlsanity.com/paper/2105.11095/) (2021)
- [SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding](https://mlsanity.com/paper/2608.03165/) (2026)

## Abstract (arXiv)

Watermarking is an operation of embedding an information into an image in a way that allows to identify ownership of the image despite applying some distortions on it. In this paper, we presented a novel end-to-end solution for embedding and recovering the watermark in the digital image using convolutional neural networks. The method is based on spreading the message over the spatial domain of the image, hence reducing the "local bits per pixel" capacity. To obtain the model we used adversarial training and applied noiser layers between the encoder and the decoder. Moreover, we broadened the spectrum of typically considered attacks on the watermark and by grouping the attacks according to their scope, we achieved high general robustness, most notably against JPEG compression, Gaussian blurring, subsampling or resizing. To help us in the models training we also proposed a precise differentiable approximation of JPEG.