cs.CVDec 10, 2025

Hierarchy-Aware Multimodal Unlearning for Medical AI

Authors: Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, Mohit Bansal

Organizations: UNC Chapel Hill · Nanyang Technological University

Abstract

Multimodal large language models (MLLMs) are increasingly used in sensitive domains such as medical AI, where privacy regulations, including HIPAA and GDPR, require the removal of specific individuals' or institutions' data. This motivates machine unlearning, which aims to remove the influence of target data from a trained model. However, existing unlearning benchmarks fail to reflect the hierarchical and multimodal structure of real-world medical data, limiting their ability to properly evaluate unlearning in practice. Therefore, we introduce MedForget, a hierarchy-aware multimodal unlearning benchmark that models data from medical institutions as a nested structure, enabling fine-grained evaluation across retain and forget splits. Experiments show that current unlearning methods struggle to achieve effective hierarchy-aware forgetting without degrading retained utility, measured by performance on clinically relevant prediction tasks. To address this limitation, we propose Cross-modal Hierarchy-Informed Projection for unlearning (CHIP), a training-free, hierarchy-aware multimodal unlearning method that deletes information by selectively removing target-specific weight subspaces while preserving sibling-shared information. Our results show that CHIP achieves the highest forget-retain performance gap across all hierarchy levels while maintaining competitive downstream utility compared to existing methods. Overall, MedForget provides a practical benchmark for evaluating hierarchy-aware multimodal unlearning for medical data, while CHIP offers an effective solution that generalizes across architectures and balances deletion with utility.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference

    Jun 5, 2026Anurag Sharma, Sai Teja Chunchu, Prasenjit Mitra +2Multi-Label ClassificationMachine Unlearning

  2. AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis

    May 28, 2026Saeedeh Davoudi, Reihaneh Iranmanesh, Ophir Frieder +1HealthcarePrivacy Leakage in Language Models

  3. ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models

    May 7, 2026Yuhang Wang, Wenjie Mei, Junkai Zhang +3Privacy-Preserving Language ModelsMultimodal Large Language Models