A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image 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_ | 1866911928345952256 |
|---|---|
| author | Ma, Rui Zhou, Qiang Jin, Yizhu Zhou, Daquan Xiao, Bangjun Li, Xiuyu Qu, Yi Singh, Aishani Keutzer, Kurt Hu, Jingtong Xie, Xiaodong Dong, Zhen Zhang, Shanghang Zhou, Shiji |
| author_facet | Ma, Rui Zhou, Qiang Jin, Yizhu Zhou, Daquan Xiao, Bangjun Li, Xiuyu Qu, Yi Singh, Aishani Keutzer, Kurt Hu, Jingtong Xie, Xiaodong Dong, Zhen Zhang, Shanghang Zhou, Shiji |
| contents | Copyright law confers upon creators the exclusive rights to reproduce, distribute, and monetize their creative works. However, recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. These technologies enable the unauthorized learning and replication of copyrighted content, artistic creations, and likenesses, leading to the proliferation of unregulated content. Notably, models like stable diffusion, which excel in text-to-image synthesis, heighten the risk of copyright infringement and unauthorized distribution.Machine unlearning, which seeks to eradicate the influence of specific data or concepts from machine learning models, emerges as a promising solution by eliminating the \enquote{copyright memories} ingrained in diffusion models. Yet, the absence of comprehensive large-scale datasets and standardized benchmarks for evaluating the efficacy of unlearning techniques in the copyright protection scenarios impedes the development of more effective unlearning methods. To address this gap, we introduce a novel pipeline that harmonizes CLIP, ChatGPT, and diffusion models to curate a dataset. This dataset encompasses anchor images, associated prompts, and images synthesized by text-to-image models. Additionally, we have developed a mixed metric based on semantic and style information, validated through both human and artist assessments, to gauge the effectiveness of unlearning approaches. Our dataset, benchmark library, and evaluation metrics will be made publicly available to foster future research and practical applications (https://rmpku.github.io/CPDM-page/, website / http://149.104.22.83/unlearning.tar.gz, dataset). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12052 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models Ma, Rui Zhou, Qiang Jin, Yizhu Zhou, Daquan Xiao, Bangjun Li, Xiuyu Qu, Yi Singh, Aishani Keutzer, Kurt Hu, Jingtong Xie, Xiaodong Dong, Zhen Zhang, Shanghang Zhou, Shiji Computer Vision and Pattern Recognition Copyright law confers upon creators the exclusive rights to reproduce, distribute, and monetize their creative works. However, recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. These technologies enable the unauthorized learning and replication of copyrighted content, artistic creations, and likenesses, leading to the proliferation of unregulated content. Notably, models like stable diffusion, which excel in text-to-image synthesis, heighten the risk of copyright infringement and unauthorized distribution.Machine unlearning, which seeks to eradicate the influence of specific data or concepts from machine learning models, emerges as a promising solution by eliminating the \enquote{copyright memories} ingrained in diffusion models. Yet, the absence of comprehensive large-scale datasets and standardized benchmarks for evaluating the efficacy of unlearning techniques in the copyright protection scenarios impedes the development of more effective unlearning methods. To address this gap, we introduce a novel pipeline that harmonizes CLIP, ChatGPT, and diffusion models to curate a dataset. This dataset encompasses anchor images, associated prompts, and images synthesized by text-to-image models. Additionally, we have developed a mixed metric based on semantic and style information, validated through both human and artist assessments, to gauge the effectiveness of unlearning approaches. Our dataset, benchmark library, and evaluation metrics will be made publicly available to foster future research and practical applications (https://rmpku.github.io/CPDM-page/, website / http://149.104.22.83/unlearning.tar.gz, dataset). |
| title | A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.12052 |