# Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification

arXiv: https://arxiv.org/abs/2604.23854 · HTML: https://mlsanity.com/paper/2604.23854/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [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)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)
- [Open Problems in Machine Unlearning for AI Safety](https://mlsanity.com/paper/2501.04952/) (2025)
- [Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects](https://mlsanity.com/paper/2403.08254/) (2024)
- [A Review on Machine Unlearning](https://mlsanity.com/paper/2411.11315/) (2024)
- [The European Union general data protection regulation: what it is and what it means](https://mlsanity.com/paper/2510.02861/) (2025)
- [Forget-MI: Machine Unlearning for Forgetting Multimodal Information in Healthcare Settings](https://mlsanity.com/paper/2506.23145/) (2025)
- [Machine Unlearning for Medical Imaging](https://mlsanity.com/paper/2407.07539/) (2024)
- [Analise de Desaprendizado de Maquina em Modelos de Classificacao de Imagens Medicas](https://mlsanity.com/paper/2508.18509/) (2025)

## Abstract (arXiv)

The application of Deep Learning in medical diagnosis must balance patient safety with compliance with data protection regulations. Machine Unlearning enables the selective removal of training data from deployed models. However, most methods are validated primarily through efficiency and privacy-oriented metrics, with limited attention to clinically asymmetric error costs. In this work, we investigate how unlearning affects clinical risk in binary medical image classification. We show that standard unlearning strategies (Fine-Tuning, Random Labeling, and SalUn) may reduce test utility while increasing false-negative rates, thereby amplifying clinical risk. To mitigate this, we propose SalUn-CRA (Clinical Risk-Aware), a variant of SalUn that replaces random relabeling with entropy-based forgetting for malignant samples in the forget set, preventing the model from learning harmful benign associations. We evaluate on DermaMNIST and PathMNIST medical image datasets under 20% and 50% data removal. Using Global Risk metrics with asymmetric costs, SalUn-CRA achieves lower or comparable clinical risk to full retraining while preserving unlearning effectiveness. These results suggest that clinical risk should be an integral component of unlearning validation in medical systems.