# Forget-MI: Machine Unlearning for Forgetting Multimodal Information in Healthcare Settings

arXiv: https://arxiv.org/abs/2506.23145 · HTML: https://mlsanity.com/paper/2506.23145/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 29 Jun 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 12 of 12)

- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher](https://mlsanity.com/paper/2205.08096/) (2022)
- [Mixed-Privacy Forgetting in Deep Networks](https://mlsanity.com/paper/2012.13431/) (2020)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Deep Unlearning via Randomized Conditionally Independent Hessians](https://mlsanity.com/paper/2204.07655/) (2022)
- [Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition](https://mlsanity.com/paper/2406.09073/) (2024)
- [Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2405.12523/) (2024)
- [Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessment](https://mlsanity.com/paper/2008.09884/) (2020)
- [Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare](https://mlsanity.com/paper/2302.09813/) (2023)
- [DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal](https://mlsanity.com/paper/2311.10448/) (2023)
- [Deep learning models are not robust against noise in clinical text](https://mlsanity.com/paper/2108.12242/) (2021)

## Built on by (most cited first, 3 of 3)

- [Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks](https://mlsanity.com/paper/2603.18570/) (2026)
- [Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification](https://mlsanity.com/paper/2604.23854/) (2026)
- [AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis](https://mlsanity.com/paper/2605.30599/) (2026)

## Abstract (arXiv)

Privacy preservation in AI is crucial, especially in healthcare, where models rely on sensitive patient data. In the emerging field of machine unlearning, existing methodologies struggle to remove patient data from trained multimodal architectures, which are widely used in healthcare. We propose Forget-MI, a novel machine unlearning method for multimodal medical data, by establishing loss functions and perturbation techniques. Our approach unlearns unimodal and joint representations of the data requested to be forgotten while preserving knowledge from the remaining data and maintaining comparable performance to the original model. We evaluate our results using performance on the forget dataset, performance on the test dataset, and Membership Inference Attack (MIA), which measures the attacker's ability to distinguish the forget dataset from the training dataset. Our model outperforms the existing approaches that aim to reduce MIA and the performance on the forget dataset while keeping an equivalent performance on the test set. Specifically, our approach reduces MIA by 0.202 and decreases AUC and F1 scores on the forget set by 0.221 and 0.305, respectively. Additionally, our performance on the test set matches that of the retrained model, while allowing forgetting. Code is available at https://github.com/BioMedIA-MBZUAI/Forget-MI.git