This paper introduces a novel deep learning framework for robust image zero-watermarking based on distortion-invariant feature learning. As a zero-watermarking scheme, our method leaves the original image unaltered and learns a reference signature through optimization in the feature space. The proposed framework consists of two key modules. In the first module, a feature extractor is trained via noise-adversarial learning to generate representations that are both invariant to distortions and semantically expressive. This is achieved by combining adversarial supervision against a distortion discriminator and a reconstruction constraint to retain image content. In the second module, we design a learning-based multibit zero-watermarking scheme where the trained invariant features are projected onto a set of trainable reference codes optimized to match a target binary message. Extensive experiments on diverse image datasets and a wide range of distortions show that our method achieves state-of-the-art robustness in both feature stability and watermark recovery. Comparative evaluations against existing self-supervised and deep watermarking techniques further highlight the superiority of our framework in generalization and robustness.

翻译：本文提出了一种新颖的深度学习框架，基于失真不变特征学习实现鲁棒图像零水印。作为一种零水印方案，我们的方法保持原始图像不变，通过特征空间中的优化学习参考签名。所提出的框架包含两个关键模块。在第一个模块中，特征提取器通过噪声对抗训练生成既对失真具有不变性又具有语义表达能力的表示，这通过结合针对失真判别器的对抗监督和保留图像内容的重构约束来实现。在第二个模块中，我们设计了一种基于学习的多比特零水印方案，将训练好的不变特征投影到一组可训练的参考码上，这些参考码经过优化以匹配目标二进制消息。在多种图像数据集和广泛失真类型上的大量实验表明，我们的方法在特征稳定性和水印恢复方面均达到了最先进的鲁棒性。与现有自监督及深度水印技术的对比评估进一步凸显了本框架在泛化能力和鲁棒性方面的优势。