WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models
This addresses the need for better evaluation tools in digital watermarking for AI-generated images, though it is incremental as it builds on existing vision-language model approaches.
The paper tackles the problem of evaluating watermarks in diffusion model-generated images by proposing WMVLM, a unified framework using vision-language models that outperforms state-of-the-art methods with strong generalization across datasets and models.
Digital watermarking is essential for securing generated images from diffusion models. Accurate watermark evaluation is critical for algorithm development, yet existing methods have significant limitations: they lack a unified framework for both residual and semantic watermarks, provide results without interpretability, neglect comprehensive security considerations, and often use inappropriate metrics for semantic watermarks. To address these gaps, we propose WMVLM, the first unified and interpretable evaluation framework for diffusion model image watermarking via vision-language models (VLMs). We redefine quality and security metrics for each watermark type: residual watermarks are evaluated by artifact strength and erasure resistance, while semantic watermarks are assessed through latent distribution shifts. Moreover, we introduce a three-stage training strategy to progressively enable the model to achieve classification, scoring, and interpretable text generation. Experiments show WMVLM outperforms state-of-the-art VLMs with strong generalization across datasets, diffusion models, and watermarking methods.