I’ve Got Proof! Dataset-Specific Watermarking for Detecting Excessive Dataset Usage in Text-to-Image Diffusion Model Fine-Tuning

Summary

The paper proposes DSW, a dataset-specific watermarking method for detecting excessive use of protected datasets when text-to-image diffusion models are fine-tuned with LoRA. An encoder embeds a watermark image representing the dataset owner's identity into the dataset samples, and a decoder trained with a bi-level optimization strategy extracts that watermark from images generated by the fine-tuned model. The authors report experiments validating the availability, effectiveness, and stealthiness of DSW.