Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations
This work addresses the problem of protecting images from copyright infringement on consumers' devices, though it is incremental as it builds upon an existing architecture.
The paper tackles the problem of digital watermarking lacking robustness against geometric transformations by proposing a new deep learning-based method that adds differentiable noise layers for JPEG estimation, rotation, rescaling, translation, shearing, and mirroring to the existing HiDDeN architecture. The result is a method that outperforms state-of-the-art approaches in geometric robustness.
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.