# ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory

arXiv: https://arxiv.org/abs/2509.13007 · HTML: https://mlsanity.com/paper/2509.13007/

## Key facts

- Cited by 5 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 21 of its 49 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- 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, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (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)
- [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)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [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)
- [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)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Federated Unlearning via Class-Discriminative Pruning](https://mlsanity.com/paper/2110.11794/) (2021)
- [HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models](https://mlsanity.com/paper/2312.14091/) (2023)
- [Erasing Undesirable Influence in Diffusion Models](https://mlsanity.com/paper/2401.05779/) (2024)

## Built on by (most cited first, 5 of 5)

- [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)
- [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)

Diffusion models excel at generating high-quality, diverse images but suffer from training data memorization, raising critical privacy and safety concerns. Data unlearning has emerged to mitigate this issue by removing the influence of specific data without retraining from scratch. We propose ReTrack, a fast and effective data unlearning method for diffusion models. ReTrack employs importance sampling to construct a more efficient fine-tuning loss, which we approximate by retaining only dominant terms. This yields an interpretable objective that redirects denoising trajectories toward the k-nearest neighbors, enabling efficient unlearning while preserving generative quality. Experiments on MNIST T-Shirt, CelebA-HQ, CIFAR-10, and Stable Diffusion show that ReTrack achieves state-of-the-art performance, striking the best trade-off between unlearning strength and generation quality preservation.