# Have you forgotten? A method to assess if machine learning models have forgotten data

arXiv: https://arxiv.org/abs/2004.10129 · HTML: https://mlsanity.com/paper/2004.10129/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 17 of 17)

- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [Machine Unlearning: A Comprehensive Survey](https://mlsanity.com/paper/2405.07406/) (2024)
- [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023)
- [Proof of Unlearning: Definitions and Instantiation](https://mlsanity.com/paper/2210.11334/) (2022)
- [Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness](https://mlsanity.com/paper/2506.06112/) (2025)
- [Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare](https://mlsanity.com/paper/2302.09813/) (2023)
- [EMA: Auditing Data Removal from Trained Models](https://mlsanity.com/paper/2109.03675/) (2021)
- [Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness](https://mlsanity.com/paper/2403.12830/) (2024)
- [Measuring Unintended Memorisation of Unique Private Features in Neural Networks](https://mlsanity.com/paper/2202.08099/) (2022)
- [XAudit : A Theoretical Look at Auditing with Explanations](https://mlsanity.com/paper/2206.04740/) (2022)
- [Attesting Distributional Properties of Training Data for Machine Learning](https://mlsanity.com/paper/2308.09552/) (2023)
- [Why patient data cannot be easily forgotten?](https://mlsanity.com/paper/2206.14541/) (2022)
- [Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction](https://mlsanity.com/paper/2405.15517/) (2024)
- [Unintended memorisation of unique features in neural networks](https://mlsanity.com/paper/2205.10079/) (2022)
- [Robust Federated Learning via Byzantine Filtering over Encrypted Updates](https://mlsanity.com/paper/2602.05410/) (2026)

## Abstract (arXiv)

In the era of deep learning, aggregation of data from several sources is a common approach to ensuring data diversity. Let us consider a scenario where several providers contribute data to a consortium for the joint development of a classification model (hereafter the target model), but, now one of the providers decides to leave. This provider requests that their data (hereafter the query dataset) be removed from the databases but also that the model `forgets' their data. In this paper, for the first time, we want to address the challenging question of whether data have been forgotten by a model. We assume knowledge of the query dataset and the distribution of a model's output. We establish statistical methods that compare the target's outputs with outputs of models trained with different datasets. We evaluate our approach on several benchmark datasets (MNIST, CIFAR-10 and SVHN) and on a cardiac pathology diagnosis task using data from the Automated Cardiac Diagnosis Challenge (ACDC). We hope to encourage studies on what information a model retains and inspire extensions in more complex settings.