# A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models

arXiv: https://arxiv.org/abs/2403.12052 · HTML: https://mlsanity.com/paper/2403.12052/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 4 Jan 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Recognizing Image Style](https://mlsanity.com/paper/1311.3715/) (2013)
- [The ArtBench Dataset: Benchmarking Generative Models with Artworks](https://mlsanity.com/paper/2206.11404/) (2022)

## Built on by (most cited first, 11 of 11)

- [Fantastic Copyrighted Beasts and How (Not) to Generate Them](https://mlsanity.com/paper/2406.14526/) (2024)
- [Deep Unlearn: Benchmarking Machine Unlearning for Image Classification](https://mlsanity.com/paper/2410.01276/) (2024)
- [Position: Bridge the Gaps between Machine Unlearning and AI Regulation](https://mlsanity.com/paper/2502.12430/) (2025)
- [Tackling Copyright Issues in AI Image Generation Through Originality Estimation and Genericization](https://mlsanity.com/paper/2406.03341/) (2024)
- [EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories](https://mlsanity.com/paper/2512.17320/) (2025)
- [Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge](https://mlsanity.com/paper/2507.07137/) (2025)
- [Benchmarking Unlearning for Vision Transformers](https://mlsanity.com/paper/2602.20114/) (2026)
- [Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion Models](https://mlsanity.com/paper/2603.00975/) (2026)
- [EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching](https://mlsanity.com/paper/2604.06063/) (2026)
- [Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending](https://mlsanity.com/paper/2605.25574/) (2026)
- [DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection](https://mlsanity.com/paper/2607.22035/) (2026)

## Abstract (arXiv)

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 enquotecopyright 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).