InvZW: Invariant Feature Learning via Noise-Adversarial Training for Robust Image Zero-Watermarking

Abstract

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.

Figures (12)

• Figure 1: Image Zero-Watermarking with Deep Learning.
• Figure 2: Modules of the Proposed Method.
• Figure 3: Module 1: Proposed Invariant Feature Learning via Noise-Adversarial Training.
• Figure 4: Proposed Reconstructor Architecture.
• Figure 5: Training Loss Curves for Invariant Feature Learning.