Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection

TL;DR

This paper introduces a universal method for embedding visible watermarks into images to provide long-term, robust copyright protection against unauthorized AI use, surpassing previous invisible watermark techniques.

Contribution

The authors propose a novel probabilistic framework for embedding hard-to-remove visible watermarks, enabling more durable copyright protection adaptable to changing AI models.

Findings

Outperforms existing invisible watermark methods in robustness.

Effective across diverse scenarios and image types.

Provides a scalable solution for long-term copyright protection.

Abstract

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI techniques such as unauthorized personalization through DreamBooth that are misused. However, these methods offer only short-term security, as they require retraining whenever the underlying model architectures change. To establish long-term protection aiming at better robustness, we go beyond invisible perturbation, and propose a universal approach that embeds \textit{visible} watermarks that are \textit{hard-to-remove} into images. Grounded in a new probabilistic and inverse problem-based formulation, our framework maximizes the discrepancy between the \textit{optimal} reconstruction and the original content. We develop an effective and efficient approximation algorithm to circumvent a intractable bi-level optimization. Experimental results demonstrate superiority of our approach across diverse scenarios.