Skip to content
GCC AI Research

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

arXiv · · Significant research

Healthcare Research Ethics Privacy LLM

Summary

Researchers from MBZUAI introduce Forget-MI, a machine unlearning method tailored for multimodal medical data, enhancing privacy by removing specific patient data from AI models. Forget-MI utilizes loss functions and perturbation techniques to unlearn both unimodal and joint data representations. The method demonstrates superior performance in reducing Membership Inference Attacks and improving data removal compared to existing techniques, while preserving overall model performance and enabling data forgetting.

Keywords

machine unlearning · multimodal data · healthcare · privacy preservation · MBZUAI

Read original article →

Get the weekly digest

Top AI stories from the GCC region, every week.

Related

A new playbook for patient privacy in the age of foundation models

MBZUAI ·

MBZUAI researchers Darya Taratynova and Shahad Hardan developed Forget-MI, a method for making clinical AI models "unlearn" specific patient data without retraining the entire model. Forget-MI addresses the challenge of removing patient data from AI models trained on multimodal records (like chest X-rays and reports) due to regulations like GDPR and HIPAA. The method unlearns both unimodal (image or text) and joint (image-text) associations while retaining overall accuracy using a late-fusion multimodal classifier. Why it matters: This research provides a practical solution to a critical privacy concern in healthcare AI, enabling compliance with data protection regulations and fostering trust in AI-driven medical applications.