English

Robust Spatial-spread Deep Neural Image Watermarking

Multimedia 2022-01-11 v2 Cryptography and Security

Abstract

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.

Keywords

Cite

@article{arxiv.2005.11735,
  title  = {Robust Spatial-spread Deep Neural Image Watermarking},
  author = {Marcin Plata and Piotr Syga},
  journal= {arXiv preprint arXiv:2005.11735},
  year   = {2022}
}

Comments

The article was accepted on TrustCom 2020: The 19th IEEE International Conference on Trust, Security and Privacy in Computing and Communications

R2 v1 2026-06-23T15:46:14.429Z