PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility
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_ | 1866910912575700992 |
|---|---|
| author | Gai, Keke Shen, Ziyue Yu, Jing Zhu, Liehuang Wu, Qi |
| author_facet | Gai, Keke Shen, Ziyue Yu, Jing Zhu, Liehuang Wu, Qi |
| contents | With the growing demand for protecting the intellectual property (IP) of text-to-image diffusion models, we propose PCDiff -- a proactive access control framework that redefines model authorization by regulating generation quality. At its core, PCDIFF integrates a trainable fuser module and hierarchical authentication layers into the decoder architecture, ensuring that only users with valid encrypted credentials can generate high-fidelity images. In the absence of valid keys, the system deliberately degrades output quality, effectively preventing unauthorized exploitation.Importantly, while the primary mechanism enforces active access control through architectural intervention, its decoupled design retains compatibility with existing watermarking techniques. This satisfies the need of model owners to actively control model ownership while preserving the traceability capabilities provided by traditional watermarking approaches.Extensive experimental evaluations confirm a strong dependency between credential verification and image quality across various attack scenarios. Moreover, when combined with typical post-processing operations, PCDIFF demonstrates powerful performance alongside conventional watermarking methods. This work shifts the paradigm from passive detection to proactive enforcement of authorization, laying the groundwork for IP management of diffusion models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11774 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility Gai, Keke Shen, Ziyue Yu, Jing Zhu, Liehuang Wu, Qi Cryptography and Security Artificial Intelligence With the growing demand for protecting the intellectual property (IP) of text-to-image diffusion models, we propose PCDiff -- a proactive access control framework that redefines model authorization by regulating generation quality. At its core, PCDIFF integrates a trainable fuser module and hierarchical authentication layers into the decoder architecture, ensuring that only users with valid encrypted credentials can generate high-fidelity images. In the absence of valid keys, the system deliberately degrades output quality, effectively preventing unauthorized exploitation.Importantly, while the primary mechanism enforces active access control through architectural intervention, its decoupled design retains compatibility with existing watermarking techniques. This satisfies the need of model owners to actively control model ownership while preserving the traceability capabilities provided by traditional watermarking approaches.Extensive experimental evaluations confirm a strong dependency between credential verification and image quality across various attack scenarios. Moreover, when combined with typical post-processing operations, PCDIFF demonstrates powerful performance alongside conventional watermarking methods. This work shifts the paradigm from passive detection to proactive enforcement of authorization, laying the groundwork for IP management of diffusion models. |
| title | PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2504.11774 |