Robust watermarking is critical for intellectual property protection, whereas existing methods face a severe vulnerability against regeneration-based AIGC attacks. We identify that existing methods fail because they entangle the watermark with high-frequency cover texture, which is susceptible to being rewritten during generative purification. To address this, we propose WaterVIB, a theoretically grounded framework that reformulates the encoder as an information sieve via the Variational Information Bottleneck. Instead of overfitting to fragile cover details, our approach forces the model to learn a Minimal Sufficient Statistic of the message. This effectively filters out redundant cover nuances prone to generative shifts, retaining only the essential signal invariant to regeneration. We theoretically prove that optimizing this bottleneck is a necessary condition for robustness against distribution-shifting attacks. Extensive experiments demonstrate that WaterVIB significantly outperforms state-of-the-art methods, achieving superior zero-shot resilience against unknown diffusion-based editing.

翻译：鲁棒水印对于知识产权保护至关重要，然而现有方法在面对基于再生的AIGC攻击时存在严重脆弱性。我们发现现有方法失败的原因在于其将水印与高频载体纹理纠缠在一起，而这类纹理在生成式净化过程中极易被重写。为解决此问题，我们提出WaterVIB——一个基于理论构建的框架，它通过变分信息瓶颈将编码器重构为信息过滤器。我们的方法不强制模型过度拟合脆弱的载体细节，而是迫使其学习消息的最小充分统计量。这能有效滤除易受生成偏移影响的冗余载体细节，仅保留对再生过程保持不变的必需信号。我们从理论上证明，优化此瓶颈是实现针对分布偏移攻击鲁棒性的必要条件。大量实验表明，WaterVIB显著优于现有先进方法，在应对未知的基于扩散的编辑攻击时展现出卓越的零样本抗性。