# Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models

arXiv: https://arxiv.org/abs/2410.18639 · HTML: https://mlsanity.com/paper/2410.18639/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 49 of its 62 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 49)

- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [New insights and perspectives on the natural gradient method](https://mlsanity.com/paper/1412.1193/) (2014)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Towards Efficient Data Valuation Based on the Shapley Value](https://mlsanity.com/paper/1902.10275/) (2019)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [Representer Point Selection for Explaining Deep Neural Networks](https://mlsanity.com/paper/1811.09720/) (2018)

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

- [CUPID: Curating Data your Robot Loves with Influence Functions](https://mlsanity.com/paper/2506.19121/) (2025)
- [A LoRA is Worth a Thousand Pictures](https://mlsanity.com/paper/2412.12048/) (2024)
- [Motion Attribution for Video Generation](https://mlsanity.com/paper/2601.08828/) (2026)
- [Nonparametric Data Attribution for Diffusion Models](https://mlsanity.com/paper/2510.14269/) (2025)
- [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)
- [The Iconicity of the Generated Image](https://mlsanity.com/paper/2509.16473/) (2025)
- [Variance Reduction for Expectations with Diffusion Teachers](https://mlsanity.com/paper/2605.21489/) (2026)
- [Sensitivity Analysis for Diffusion Models](https://mlsanity.com/paper/2509.23092/) (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)
- [When Sample Selection Bias Precipitates Model Collapse](https://mlsanity.com/paper/2606.13732/) (2026)
- [Constraint-Aware Influence Estimation in Deep Constrained Learning](https://mlsanity.com/paper/2607.23388/) (2026)
- [Traceable Spectral Inference via Influence Functions: Efficient Data Attribution and Error Proxies for the Ariel Mission](https://mlsanity.com/paper/2608.23458/) (2026)
- [SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models](https://mlsanity.com/paper/2601.22276/) (2026)
- [GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning](https://mlsanity.com/paper/2601.22651/) (2026)
- [On the Fragility of Data Attribution When Learning Is Distributed](https://mlsanity.com/paper/2605.15520/) (2026)
- [Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety](https://mlsanity.com/paper/2607.05407/) (2026)
- [FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding](https://mlsanity.com/paper/2607.21615/) (2026)
- [DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection](https://mlsanity.com/paper/2607.22035/) (2026)
- [Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution](https://mlsanity.com/paper/2609.38776/) (2026)

## Abstract (arXiv)

As diffusion models become increasingly popular, the misuse of copyrighted and private images has emerged as a major concern. One promising solution to mitigate this issue is identifying the contribution of specific training samples in generative models, a process known as data attribution. Existing data attribution methods for diffusion models typically quantify the contribution of a training sample by evaluating the change in diffusion loss when the sample is included or excluded from the training process. However, we argue that the direct usage of diffusion loss cannot represent such a contribution accurately due to the calculation of diffusion loss. Specifically, these approaches measure the divergence between predicted and ground truth distributions, which leads to an indirect comparison between the predicted distributions and cannot represent the variances between model behaviors. To address these issues, we aim to measure the direct comparison between predicted distributions with an attribution score to analyse the training sample importance, which is achieved by Diffusion Attribution Score (textitDAS). Underpinned by rigorous theoretical analysis, we elucidate the effectiveness of DAS. Additionally, we explore strategies to accelerate DAS calculations, facilitating its application to large-scale diffusion models. Our extensive experiments across various datasets and diffusion models demonstrate that DAS significantly surpasses previous benchmarks in terms of the linear data-modelling score, establishing new state-of-the-art performance. Code is available at hyperlinkherehttps://github.com/Jinxu-Lin/DAS.