Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data

• URL: http://arxiv.org/abs/2511.19498v1
• Date: Sun, 23 Nov 2025 15:28:19 GMT
• Title: Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data
• Authors: Yi Zhang, Tianxiang Xu, Zijian Li, Chao Zhang, Kunyu Zhang, Zhan Gao, Meinuo Li, Xiaohan Zhang, Qichao Qi, Bing Chen,
• Abstract summary: Large language models (LLMs) exhibit exceptional performance but pose substantial privacy risks.<n>We present a hierarchical dual-strategy framework for selective knowledge unlearning.<n>Our framework maintains robust privacy guarantees while requiring modification of only 0.1% of parameters.
• Score: 15.916549580598462
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) exhibit exceptional performance but pose substantial privacy risks due to training data memorization, particularly within healthcare contexts involving imperfect or privacy-sensitive patient information. We present a hierarchical dual-strategy framework for selective knowledge unlearning that precisely removes specialized knowledge while preserving fundamental medical competencies. Our approach synergistically integrates geometric-constrained gradient updates to selectively modulate target parameters with concept-aware token-level interventions that distinguish between preservation-critical and unlearning-targeted tokens via a unified four-level medical concept hierarchy. Comprehensive evaluations on the MedMCQA (surgical) and MHQA (anxiety, depression, trauma) datasets demonstrate superior performance, achieving an 82.7% forgetting rate and 88.5% knowledge preservation. Notably, our framework maintains robust privacy guarantees while requiring modification of only 0.1% of parameters, addressing critical needs for regulatory compliance, auditability, and ethical standards in clinical research.

Related papers

• Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation [97.36081721024728]
  We propose the first benchmark for assessing confidence in multi-turn interaction during realistic medical consultations.<n>Our benchmark unifies three types of medical data for open-ended diagnostic generation.<n>We present MedConf, an evidence-grounded linguistic self-assessment framework.
  arXiv  Detail & Related papers  (2026-01-22T04:51:39Z)
• Responsible Evaluation of AI for Mental Health [72.85175110624736]
  Current approaches to evaluating AI tools in mental health care are fragmented and poorly aligned with clinical practice, social context, and first-hand user experience.<n>This paper argues for a rethinking of responsible evaluation by introducing an interdisciplinary framework that integrates clinical soundness, social context, and equity.
  arXiv  Detail & Related papers  (2026-01-20T12:55:10Z)
• MedHE: Communication-Efficient Privacy-Preserving Federated Learning with Adaptive Gradient Sparsification for Healthcare [0.0]
  This paper presents MedHE, a novel framework combining adaptive gradient sparsification with CKKS homomorphic encryption to enable privacy-preserving collaborative learning on sensitive medical data.<n>Our approach introduces a dynamic threshold mechanism with error compensation for top-k gradient selection, achieving 97.5 percent communication reduction while preserving model utility.
  arXiv  Detail & Related papers  (2025-11-12T06:50:48Z)
• Exploring Membership Inference Vulnerabilities in Clinical Large Language Models [42.52690697965999]
  We present an exploratory empirical study on membership inference vulnerabilities in clinical large language models (LLMs)<n>Using a state-of-the-art clinical question-answering model, Llemr, we evaluate both canonical loss-based attacks and a domain-motivated paraphrasing-based perturbation strategy.<n>Results motivate continued development of context-aware, domain-specific privacy evaluations and defenses.
  arXiv  Detail & Related papers  (2025-10-21T14:27:48Z)
• A Semantic Framework for Patient Digital Twins in Chronic Care [0.0]
  The Patient Medical Digital Twin (PMDT) integrates physiological, psychosocial, behavioral, and genomic information into a coherent model.<n>The PMDT ensures semantic interoperability, supports automated reasoning, and enables reuse across diverse clinical contexts.<n>By bridging gaps in data fragmentation and semantic standardization, the PMDT provides a validated foundation for next-generation digital health ecosystems.
  arXiv  Detail & Related papers  (2025-10-10T08:34:55Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunities [58.61680631581921]
  Mental health disorders create profound personal and societal burdens, yet conventional diagnostics are resource-intensive and limit accessibility.<n>This paper examines these challenges and proposes solutions, including anonymization, synthetic data, and privacy-preserving training.<n>It aims to advance reliable, privacy-aware AI tools that support clinical decision-making and improve mental health outcomes.
  arXiv  Detail & Related papers  (2025-02-01T15:10:02Z)
• Artificial Intelligence-Driven Clinical Decision Support Systems [5.010570270212569]
  The chapter emphasizes that creating trustworthy AI systems in healthcare requires careful consideration of fairness, explainability, and privacy.<n>The challenge of ensuring equitable healthcare delivery through AI is stressed, discussing methods to identify and mitigate bias in clinical predictive models.<n>The discussion advances in an analysis of privacy vulnerabilities in medical AI systems, from data leakage in deep learning models to sophisticated attacks against model explanations.
  arXiv  Detail & Related papers  (2025-01-16T16:17:39Z)
• Empowering Healthcare through Privacy-Preserving MRI Analysis [3.6394715554048234]
  We introduce the Ensemble-Based Federated Learning (EBFL) Framework. EBFL framework deviates from the conventional approach by emphasizing model features over sharing sensitive patient data. We have achieved remarkable precision in the classification of brain tumors, including glioma, meningioma, pituitary, and non-tumor instances.
  arXiv  Detail & Related papers  (2024-03-14T19:51:18Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching [49.78442796596806]
  We propose an innovative privacy-aware data augmentation approach for patient-trial matching (LLM-PTM) Our experiments demonstrate a 7.32% average improvement in performance using the proposed LLM-PTM method, and the generalizability to new data is improved by 12.12%.
  arXiv  Detail & Related papers  (2023-03-24T03:14:00Z)
• Privacy-preserving medical image analysis [53.4844489668116]
  We present PriMIA, a software framework designed for privacy-preserving machine learning (PPML) in medical imaging. We show significantly better classification performance of a securely aggregated federated learning model compared to human experts on unseen datasets. We empirically evaluate the framework's security against a gradient-based model inversion attack.
  arXiv  Detail & Related papers  (2020-12-10T13:56:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.