A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models
- URL: http://arxiv.org/abs/2403.12052v3
- Date: Fri, 21 Jun 2024 14:58:30 GMT
- Title: A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models
- Authors: Rui Ma, Qiang Zhou, Yizhu Jin, Daquan Zhou, Bangjun Xiao, Xiuyu Li, Yi Qu, Aishani Singh, Kurt Keutzer, Jingtong Hu, Xiaodong Xie, Zhen Dong, Shanghang Zhang, Shiji Zhou,
- Abstract summary: Copyright law confers creators the exclusive rights to reproduce, distribute, and monetize their creative works.
Recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement.
We introduce a novel pipeline that harmonizes CLIP, ChatGPT, and diffusion models to curate a dataset.
- Score: 52.49582606341111
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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).
Related papers
- Evaluating Copyright Takedown Methods for Language Models [100.38129820325497]
Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material.
This paper introduces the first evaluation of the feasibility and side effects of copyright takedowns for LMs.
We examine several strategies, including adding system prompts, decoding-time filtering interventions, and unlearning approaches.
arXiv Detail & Related papers (2024-06-26T18:09:46Z) - EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations [73.94175015918059]
We introduce a novel approach, EnTruth, which Enhances Traceability of unauthorized dataset usage.
By strategically incorporating the template memorization, EnTruth can trigger the specific behavior in unauthorized models as the evidence of infringement.
Our method is the first to investigate the positive application of memorization and use it for copyright protection, which turns a curse into a blessing.
arXiv Detail & Related papers (2024-06-20T02:02:44Z) - Protect-Your-IP: Scalable Source-Tracing and Attribution against Personalized Generation [19.250673262185767]
We propose a unified approach for image copyright source-tracing and attribution.
We introduce an innovative watermarking-attribution method that blends proactive and passive strategies.
We have conducted experiments using various celebrity portrait series sourced online.
arXiv Detail & Related papers (2024-05-26T15:14:54Z) - Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability.
We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images.
Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
arXiv Detail & Related papers (2024-03-28T22:25:05Z) - CopyScope: Model-level Copyright Infringement Quantification in the
Diffusion Workflow [6.6282087165087304]
Copyright infringement quantification is the primary and challenging step towards AI-generated image copyright traceability.
We propose CopyScope, a new framework to quantify the infringement of AI-generated images from the model level.
arXiv Detail & Related papers (2023-10-13T13:08:09Z) - On Copyright Risks of Text-to-Image Diffusion Models [31.982360758956034]
Diffusion models excel in creating images from text prompts, a task referred to as text-to-image (T2I) generation.
Recent studies have studied the copyright behavior of diffusion models when using direct, copyrighted prompts.
Our research extends this by examining subtler forms of infringement, where even indirect prompts can trigger copyright issues.
arXiv Detail & Related papers (2023-09-15T01:34:02Z) - Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images
with Free Attention Masks [64.67735676127208]
Text-to-image diffusion models have shown great potential for benefiting image recognition.
Although promising, there has been inadequate exploration dedicated to unsupervised learning on diffusion-generated images.
We introduce customized solutions by fully exploiting the aforementioned free attention masks.
arXiv Detail & Related papers (2023-08-13T10:07:46Z) - DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models [79.71665540122498]
We propose a method for detecting unauthorized data usage by planting the injected content into the protected dataset.
Specifically, we modify the protected images by adding unique contents on these images using stealthy image warping functions.
By analyzing whether the model has memorized the injected content, we can detect models that had illegally utilized the unauthorized data.
arXiv Detail & Related papers (2023-07-06T16:27:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.