DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909627635990528 |
|---|---|
| author | Lei, Liangqi Gai, Keke Yu, Jing Zhu, Liehuang |
| author_facet | Lei, Liangqi Gai, Keke Yu, Jing Zhu, Liehuang |
| contents | Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating potential risks associated with Artificial Intelligence (AI)-generated contents. However, post-processed watermarking methods are unable to withstand generative watermark attacks and there exists a trade-off between image fidelity and watermark strength. Therefore, we propose a novel technique called DiffuseTrace. DiffuseTrace does not rely on fine-tuning of the diffusion model components. The multi-bit watermark is a embedded into the image space semantically without compromising image quality. The watermark component can be utilized as a plug-in in arbitrary diffusion models. We validate through experiments the effectiveness and flexibility of DiffuseTrace. Under 8 types of image processing watermark attacks and 3 types of generative watermark attacks, DiffuseTrace maintains watermark detection rate of 99% and attribution accuracy of over 94%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02696 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model Lei, Liangqi Gai, Keke Yu, Jing Zhu, Liehuang Cryptography and Security Artificial Intelligence Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating potential risks associated with Artificial Intelligence (AI)-generated contents. However, post-processed watermarking methods are unable to withstand generative watermark attacks and there exists a trade-off between image fidelity and watermark strength. Therefore, we propose a novel technique called DiffuseTrace. DiffuseTrace does not rely on fine-tuning of the diffusion model components. The multi-bit watermark is a embedded into the image space semantically without compromising image quality. The watermark component can be utilized as a plug-in in arbitrary diffusion models. We validate through experiments the effectiveness and flexibility of DiffuseTrace. Under 8 types of image processing watermark attacks and 3 types of generative watermark attacks, DiffuseTrace maintains watermark detection rate of 99% and attribution accuracy of over 94%. |
| title | DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2405.02696 |