JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
This addresses the problem of protecting image watermarks against advanced AI edits for content creators and platforms, representing a novel method rather than an incremental improvement.
The paper tackles the vulnerability of image watermarks to diffusion-model-based editing by introducing JIGMARK, a black-box watermarking technique that uses contrastive learning without gradient access, achieving a True Positive Rate more than triple that of leading baselines at a 1% False Positive Rate while maintaining image quality.
In this study, we investigate the vulnerability of image watermarks to diffusion-model-based image editing, a challenge exacerbated by the computational cost of accessing gradient information and the closed-source nature of many diffusion models. To address this issue, we introduce JIGMARK. This first-of-its-kind watermarking technique enhances robustness through contrastive learning with pairs of images, processed and unprocessed by diffusion models, without needing a direct backpropagation of the diffusion process. Our evaluation reveals that JIGMARK significantly surpasses existing watermarking solutions in resilience to diffusion-model edits, demonstrating a True Positive Rate more than triple that of leading baselines at a 1% False Positive Rate while preserving image quality. At the same time, it consistently improves the robustness against other conventional perturbations (like JPEG, blurring, etc.) and malicious watermark attacks over the state-of-the-art, often by a large margin. Furthermore, we propose the Human Aligned Variation (HAV) score, a new metric that surpasses traditional similarity measures in quantifying the number of image derivatives from image editing.