# Data Attribution for Text-to-Image Models by Unlearning Synthesized Images

arXiv: https://arxiv.org/abs/2406.09408 · HTML: https://mlsanity.com/paper/2406.09408/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security.
- Builds on 69 of its 75 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Placed in

- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 30 of 69)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [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)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Scaling up GANs for Text-to-Image Synthesis](https://mlsanity.com/paper/2303.05511/) (2023)
- [Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors](https://mlsanity.com/paper/2203.13131/) (2022)

## Built on by (most cited first, 22 of 22)

- [EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment](https://mlsanity.com/paper/2511.00804/) (2025)
- [A LoRA is Worth a Thousand Pictures](https://mlsanity.com/paper/2412.12048/) (2024)
- [Position: Bridge the Gaps between Machine Unlearning and AI Regulation](https://mlsanity.com/paper/2502.12430/) (2025)
- [Fast Data Attribution for Text-to-Image Models](https://mlsanity.com/paper/2511.10721/) (2025)
- [Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods](https://mlsanity.com/paper/2412.03906/) (2024)
- [IntroStyle: Training-Free Introspective Style Attribution using Diffusion Features](https://mlsanity.com/paper/2412.14432/) (2024)
- [Learning to Weight Parameters for Training Data Attribution](https://mlsanity.com/paper/2506.05647/) (2025)
- [Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution](https://mlsanity.com/paper/2507.06547/) (2025)
- [Attribution-by-design: Ensuring Inference-Time Provenance in Generative Music Systems](https://mlsanity.com/paper/2510.08062/) (2025)
- [Deep Sketch-Based 3D Modeling: A Survey](https://mlsanity.com/paper/2603.03287/) (2026)
- [The Iconicity of the Generated Image](https://mlsanity.com/paper/2509.16473/) (2025)
- [Identifying Prompted Artist Names from Generated Images](https://mlsanity.com/paper/2507.18633/) (2025)
- [Coffee: Controllable Diffusion Fine-tuning](https://mlsanity.com/paper/2511.14113/) (2025)
- [Unsupervised Synthetic Image Attribution: Alignment and Disentanglement](https://mlsanity.com/paper/2601.22663/) (2026)
- [Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew](https://mlsanity.com/paper/2605.17938/) (2026)
- [GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning](https://mlsanity.com/paper/2601.22651/) (2026)
- [ROKA: Robust Knowledge Unlearning against Adversaries](https://mlsanity.com/paper/2603.00436/) (2026)
- [On the Fragility of Data Attribution When Learning Is Distributed](https://mlsanity.com/paper/2605.15520/) (2026)
- [Data Attribution in Large Language Models via Bidirectional Gradient Optimization](https://mlsanity.com/paper/2606.04928/) (2026)
- [FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding](https://mlsanity.com/paper/2607.21615/) (2026)
- [Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution](https://mlsanity.com/paper/2609.38776/) (2026)
- [TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models](https://mlsanity.com/paper/2610.00835/) (2026)

## Abstract (arXiv)

The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image. Influence is defined such that, for a given output, if a model is retrained from scratch without the most influential images, the model would fail to reproduce the same output. Unfortunately, directly searching for these influential images is computationally infeasible, since it would require repeatedly retraining models from scratch. In our work, we propose an efficient data attribution method by simulating unlearning the synthesized image. We achieve this by increasing the training loss on the output image, without catastrophic forgetting of other, unrelated concepts. We then identify training images with significant loss deviations after the unlearning process and label these as influential. We evaluate our method with a computationally intensive but "gold-standard" retraining from scratch and demonstrate our method's advantages over previous methods.