Disguised Copyright Infringement of Latent Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929371486355456 |
|---|---|
| author | Lu, Yiwei Yang, Matthew Y. R. Liu, Zuoqiu Kamath, Gautam Yu, Yaoliang |
| author_facet | Lu, Yiwei Yang, Matthew Y. R. Liu, Zuoqiu Kamath, Gautam Yu, Yaoliang |
| contents | Copyright infringement may occur when a generative model produces samples substantially similar to some copyrighted data that it had access to during the training phase. The notion of access usually refers to including copyrighted samples directly in the training dataset, which one may inspect to identify an infringement. We argue that such visual auditing largely overlooks a concealed copyright infringement, where one constructs a disguise that looks drastically different from the copyrighted sample yet still induces the effect of training Latent Diffusion Models on it. Such disguises only require indirect access to the copyrighted material and cannot be visually distinguished, thus easily circumventing the current auditing tools. In this paper, we provide a better understanding of such disguised copyright infringement by uncovering the disguises generation algorithm, the revelation of the disguises, and importantly, how to detect them to augment the existing toolbox. Additionally, we introduce a broader notion of acknowledgment for comprehending such indirect access. Our code is available at https://github.com/watml/disguised_copyright_infringement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06737 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Disguised Copyright Infringement of Latent Diffusion Models Lu, Yiwei Yang, Matthew Y. R. Liu, Zuoqiu Kamath, Gautam Yu, Yaoliang Machine Learning Cryptography and Security Copyright infringement may occur when a generative model produces samples substantially similar to some copyrighted data that it had access to during the training phase. The notion of access usually refers to including copyrighted samples directly in the training dataset, which one may inspect to identify an infringement. We argue that such visual auditing largely overlooks a concealed copyright infringement, where one constructs a disguise that looks drastically different from the copyrighted sample yet still induces the effect of training Latent Diffusion Models on it. Such disguises only require indirect access to the copyrighted material and cannot be visually distinguished, thus easily circumventing the current auditing tools. In this paper, we provide a better understanding of such disguised copyright infringement by uncovering the disguises generation algorithm, the revelation of the disguises, and importantly, how to detect them to augment the existing toolbox. Additionally, we introduce a broader notion of acknowledgment for comprehending such indirect access. Our code is available at https://github.com/watml/disguised_copyright_infringement. |
| title | Disguised Copyright Infringement of Latent Diffusion Models |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2404.06737 |