CVPR Findings2026
Evaluating Dataset Watermarking for Fine-Tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach
Xincheng Wang, Hanchi Sun, Wenjun Sun, Kejun Xue, Wangqiu Zhou, Jianbo Zhang, Wei Sun, Dandan Zhu, Xiongkuo Min, Jun Jia, Zhijun Fang
Abstract
Recently, numerous fine-tuning techniques for diffusion models have been developed, enabling diffusion models to generate content that closely resembles a specific image set, such as specific facial identities and artistic styles. However, this advancement also poses potential security risks. The primary risk comes from copyright violations due to using public domain images without authorization to finetune diffusion models. Furthermore, if such models generate harmful content linked to the source images, tracing the origin of the fine-tuning data is crucial to clarify responsibility. To achieve fine-tuning traceability of customized diffusion models, dataset watermarking for diffusion model has been proposed, involving embedding imperceptible watermarks into images that require traceability. Notably, even after using the watermarked images to finetune diffusion models, the watermarks remain detectable in the generated outputs. However, existing dataset watermarking approaches lack a unified framework for performance evaluation, thereby limiting their effectiveness in practical scenarios. To address this gap, this paper first establishes a generalized threat model and subsequently introduces a comprehensive framework for evaluating dataset watermarking methods, comprising three dimensions: Universality, Transmissibility, and Robustness. Our evaluation results demonstrate that existing methods exhibit universality across diverse fine-tuning approaches and tasks, as well as transmissibility even when only a small proportion of watermarked images is used. In terms of robustness, existing methods show good performance against common image proces sing operations, but this does not match realworld threat scenarios. To address this issue, this paper proposes a practical watermark removal method that can completely remove dataset watermarks without affecting fine-tuning, revealing their vulnerabilities and pointing to a new challenge for future research.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on24
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Improved Techniques for Training Score-Based Generative ModelsYang Song, Stefano ErmonNeurIPS 2020 · 1,527 citations
- Exploring CLIP for Assessing the Look and Feel of ImagesJianyi Wang, Kelvin C. K. Chan, Chen Change LoyAAAI 2023 · 1,208 citations
- Cold Diffusion: Inverting Arbitrary Image Transforms Without NoiseArpit Bansal, Eitan Borgnia, Hong-Min Chu, Jie Li et al.NeurIPS 2023 · 469 citations
Related papers
- NSGuard: Null-Space Guided Robust Watermarking for Data Copyright Protection in Customized GenerationLizhi Xiong, Jianguo Feng, Ziqiang Li, Jun Li, Weiwei Jiang, Zhangjie FuCVPR Findings 2026
- RECOVER: Reliable Detection of Unauthorized Data Usage in Text-to-Image Diffusion Models via Inversion RobustnessYanhao Wei, Xiaokang Zhao, Boheng Li, Yang Zhang et al.ICML 2026
- RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion ModelsYingsha Xie, Rui Min, Zeyu Qin, Fei Ma et al.NeurIPS 2025 · 3 citations
- DVW: Diffusion Visible WatermarkJiawei Zhang, Xiaoli Jiang, Hao Wang, Lin Yuan et al.ACM MM 2025 · 1 citation
- Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion ModelsWenda Li, Huijie Zhang, Qing QuNeurIPS 2025 · 8 citations
