MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914095781904384 |
|---|---|
| author | Pan, Leyi Guan, Sheng Fu, Zheyu Si, Luyang Wang, Huan Wang, Zian Li, Hanqian Hu, Xuming King, Irwin Yu, Philip S. Liu, Aiwei Wen, Lijie |
| author_facet | Pan, Leyi Guan, Sheng Fu, Zheyu Si, Luyang Wang, Huan Wang, Zian Li, Hanqian Hu, Xuming King, Irwin Yu, Philip S. Liu, Aiwei Wen, Lijie |
| contents | We introduce MarkDiffusion, an open-source Python toolkit for generative watermarking of latent diffusion models. It comprises three key components: a unified implementation framework for streamlined watermarking algorithm integrations and user-friendly interfaces; a mechanism visualization suite that intuitively showcases added and extracted watermark patterns to aid public understanding; and a comprehensive evaluation module offering standard implementations of 24 tools across three essential aspects - detectability, robustness, and output quality - plus 8 automated evaluation pipelines. Through MarkDiffusion, we seek to assist researchers, enhance public awareness and engagement in generative watermarking, and promote consensus while advancing research and applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10569 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models Pan, Leyi Guan, Sheng Fu, Zheyu Si, Luyang Wang, Huan Wang, Zian Li, Hanqian Hu, Xuming King, Irwin Yu, Philip S. Liu, Aiwei Wen, Lijie Cryptography and Security Artificial Intelligence Multimedia 68T50 I.2.7 We introduce MarkDiffusion, an open-source Python toolkit for generative watermarking of latent diffusion models. It comprises three key components: a unified implementation framework for streamlined watermarking algorithm integrations and user-friendly interfaces; a mechanism visualization suite that intuitively showcases added and extracted watermark patterns to aid public understanding; and a comprehensive evaluation module offering standard implementations of 24 tools across three essential aspects - detectability, robustness, and output quality - plus 8 automated evaluation pipelines. Through MarkDiffusion, we seek to assist researchers, enhance public awareness and engagement in generative watermarking, and promote consensus while advancing research and applications. |
| title | MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models |
| topic | Cryptography and Security Artificial Intelligence Multimedia 68T50 I.2.7 |
| url | https://arxiv.org/abs/2509.10569 |