Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations

TL;DR

This paper introduces a deep learning-based image watermarking method that is highly robust against geometric transformations, enhancing copyright protection for digital images.

Contribution

It extends the HiDDeN architecture with new differentiable noise layers to improve robustness against geometric attacks.

Findings

Outperforms existing methods in geometric robustness

Effective against rotation, rescaling, translation, shearing, and mirroring

Suitable for protecting images on consumer devices

Abstract

Digital watermarking enables protection against copyright infringement of images. Although existing methods embed watermarks imperceptibly and demonstrate robustness against attacks, they typically lack resilience against geometric transformations. Therefore, this paper proposes a new watermarking method that is robust against geometric attacks. The proposed method is based on the existing HiDDeN architecture that uses deep learning for watermark encoding and decoding. We add new noise layers to this architecture, namely for a differentiable JPEG estimation, rotation, rescaling, translation, shearing and mirroring. We demonstrate that our method outperforms the state of the art when it comes to geometric robustness. In conclusion, the proposed method can be used to protect images when viewed on consumers' devices.