CASIAL: Geometric Distortion Robust Image Watermarking

Yupeng Qiu, Han Fang, Ee-Chien Chang

Keywords: deep learning-based watermarking

Abstract: Deep learning–based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations remains limited. Such transformations induce two fundamental failure modes: region removal, such as cropping or masking, which eliminates the information carried by removed pixels, and desynchronization, such as scaling or rotation, which misaligns pixel positions and disrupts decoding. We argue that achieving geometric robustness requires two essential properties: (1) global spread of the watermark message, ensuring resilience even when large regions are removed, and (2) geometry-invariant representations, enabling decoding to remain synchronized despite spatial transformations. To realize these properties, we propose CASIAL, a geometric distortion–robust watermarking framework with cover image-aware message spreading (CAS) and invariance alignment learning (IAL). CAS tightly couples watermark bits with cover image features and distributes them adaptively across the entire image, enhancing per-pixel information capacity and robustness to region removal. IAL leverages spatial attention to capture cross-pixel dependencies and align perturbed features into a shared geometry-invariant representation space, mitigating failures due to desynchronization. Extensive experiments demonstrate that CASIAL achieves state-of-the-art robustness against challenging geometric distortions, while maintaining high visual fidelity and decoding accuracy.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 10522