AI 中文总结
该研究针对深度学习水印在几何变换下鲁棒性不足的问题，提出含CAS策略和IAL模块的CASIAL框架，经实验验证其几何鲁棒性等性能优于现有基线，且视觉质量优异。
AI 中文摘要
基于深度学习的水印技术对非几何失真具有较强鲁棒性，但其在几何变换下的性能仍有限。这类变换会引发两种基本失效模式：一是区域移除，如裁剪或遮蔽，会消除被移除像素携带的信息；二是失同步，如缩放或旋转，会使像素位置错位并干扰解码。我们认为，实现几何鲁棒性需要两个关键特性：（1）水印信息的全局扩散，确保即使大面积区域被移除仍能保持鲁棒性；（2）几何不变表示，使解码在空间变换下仍能保持同步。基于这些见解，我们提出CASIAL，这是一个抗几何失真的水印框架，包含感知载体图像的信息扩散（CAS）策略和不变性对齐学习（IAL）模块。CAS将水印比特与载体图像特征紧密耦合，并自适应地分布在整个图像中，提升了每个像素的信息容量和对区域移除的鲁棒性。IAL利用空间注意力捕捉跨像素依赖关系，并将受扰动的特征对齐到共享的几何不变表示空间，缓解失同步导致的失效。在六种具有挑战性的几何变换下，CASIAL的鲁棒性显著优于十一种现有基线，同时保持了较高的视觉质量。它在六种信号失真和四种光度变换下也保持了有竞争力的性能。值得注意的是，尽管仅在白盒失真下训练，CASIAL对未见过的黑盒失真也表现出较强的迁移鲁棒性。综合实验证明了我们方法的广泛鲁棒性和优异视觉质量。
英文摘要
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. Building on these insights, we propose CASIAL, a geometric distortion-robust watermarking framework with cover image-aware message spreading (CAS) strategy and invariance alignment learning (IAL) module. 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. Across six challenging geometric transformations, CASIAL achieves substantially stronger robustness than eleven prior baselines while preserving high visual quality. It also maintains competitive performance under six signal distortions and four photometric transformations. Notably, although trained only with white-box distortions, CASIAL also exhibits strong transfer robustness to unseen black-box distortions. Comprehensive experiments demonstrate the broad robustness and superior visual quality of our method.
Comments14 pages, 9 figures, 6 tables. Supplementary material included
