# Data Unlearning in Diffusion Models

arXiv: https://arxiv.org/abs/2503.01034 · HTML: https://mlsanity.com/paper/2503.01034/

## Key facts

- Cited by 18 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 34 of its 42 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 34)

- [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)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [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)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [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)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Understanding and Mitigating Copying in Diffusion Models](https://mlsanity.com/paper/2305.20086/) (2023)
- [Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models](https://mlsanity.com/paper/2305.10120/) (2023)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [Detecting, Explaining, and Mitigating Memorization in Diffusion Models](https://mlsanity.com/paper/2407.21720/) (2024)
- [A Reproducible Extraction of Training Images from Diffusion Models](https://mlsanity.com/paper/2305.08694/) (2023)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [Machine Unlearning for Image-to-Image Generative Models](https://mlsanity.com/paper/2402.00351/) (2024)
- [Deep Regression Unlearning](https://mlsanity.com/paper/2210.08196/) (2022)
- [Training Data Protection with Compositional Diffusion Models](https://mlsanity.com/paper/2308.01937/) (2023)

## Built on by (most cited first, 18 of 18)

- [wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models](https://mlsanity.com/paper/2507.08838/) (2025)
- [ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code](https://mlsanity.com/paper/2506.02314/) (2025)
- [Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges](https://mlsanity.com/paper/2507.19672/) (2025)
- [Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression](https://mlsanity.com/paper/2505.19398/) (2025)
- [Is your algorithm unlearning or untraining?](https://mlsanity.com/paper/2604.07962/) (2026)
- [Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules](https://mlsanity.com/paper/2606.08802/) (2026)
- [Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning](https://mlsanity.com/paper/2510.17917/) (2025)
- [Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints](https://mlsanity.com/paper/2605.30825/) (2026)
- [GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention](https://mlsanity.com/paper/2507.13598/) (2025)
- [IMU: Influence-guided Machine Unlearning](https://mlsanity.com/paper/2508.01620/) (2025)
- [Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models](https://mlsanity.com/paper/2603.10445/) (2026)
- [Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew](https://mlsanity.com/paper/2605.17938/) (2026)
- [PIU: Proximity-guided Identity Unlearning in ID-Conditioned Diffusion Models](https://mlsanity.com/paper/2605.22311/) (2026)
- [Adaptive-lambda Subtracted Importance Sampled Scores in Machine Unlearning for DDPMs and VAEs](https://mlsanity.com/paper/2512.01054/) (2025)
- [You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2603.00133/) (2026)
- [Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning](https://mlsanity.com/paper/2609.25166/) (2026)
- [Continual Data Unlearning in Diffusion Models via Transition-based Regularization](https://mlsanity.com/paper/2609.32328/) (2026)
- [Data Unlearning via Inverse Distillation](https://mlsanity.com/paper/2609.36099/) (2026)

## Abstract (arXiv)

Recent work has shown that diffusion models memorize and reproduce training data examples. At the same time, large copyright lawsuits and legislation such as GDPR have highlighted the need for erasing datapoints from diffusion models. However, retraining from scratch is often too expensive. This motivates the setting of data unlearning, i.e., the study of efficient techniques for unlearning specific datapoints from the training set. Existing concept unlearning techniques require an anchor prompt/class/distribution to guide unlearning, which is not available in the data unlearning setting. General-purpose machine unlearning techniques were found to be either unstable or failed to unlearn data. We therefore propose a family of new loss functions called Subtracted Importance Sampled Scores (SISS) that utilize importance sampling and are the first method to unlearn data with theoretical guarantees. SISS is constructed as a weighted combination between simpler objectives that are responsible for preserving model quality and unlearning the targeted datapoints. When evaluated on CelebA-HQ and MNIST, SISS achieved Pareto optimality along the quality and unlearning strength dimensions. On Stable Diffusion, SISS successfully mitigated memorization on nearly 90% of the prompts we tested.