mlsanityData to 14 Oct 2026

SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations

arXiv 2601.10004 ↗First posted 15 Jan 2026cs.CR cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) are increasingly adopted in healthcare to support clinical decision-making, summarize electronic health records (EHRs), and enhance patient care. However, this integration introduces significant privacy and security challenges, driven by the sensitivity of clinical data and the high-stakes nature of medical workflows. These risks become even more pronounced across heterogeneous deployment environments, ranging from small on-premise hospital systems to regional health networks, each with unique resource limitations and regulatory demands. This Systematization of Knowledge (SoK) examines the evolving threat landscape across the three core LLM phases: Data preprocessing, Fine-tuning, and Inference within realistic healthcare settings. We present a detailed threat model that characterizes adversaries, capabilities, and attack surfaces at each phase, and we systematize how existing privacy-preserving techniques (PPTs) attempt to mitigate these vulnerabilities. While existing defenses show promise, our analysis identifies persistent limitations in securing sensitive clinical data across diverse operational tiers. We conclude with phase-aware recommendations and future research directions aimed at strengthening privacy guarantees for LLMs in regulated environments. This work provides a foundation for understanding the intersection of LLMs, threats, and privacy in healthcare, offering a roadmap toward more robust and clinically trustworthy AI systems.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 44 of its 90 references that are in the map. First posted on arXiv 15 Jan 2026.

Builds on

44 of 90 references.

References · 44

  1. 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 325
  2. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
  3. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
  4. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 186
  5. 2024FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptationscited by 146
  6. 2020Synthetic Data -- Anonymisation Groundhog Daycited by 108
  7. 2023Conversational Health Agents: A Personalized LLM-Powered Agent Frameworkcited by 92
  8. 2023DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Passcited by 67
  9. 2024SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 62
  10. 2024FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuningcited by 59
  11. 2024Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approachescited by 52
  12. 2023Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notescited by 51
32 more
  1. 2023Privacy in Large Language Models: Attacks, Defenses and Future Directionscited by 51
  2. 2023CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcarecited by 43
  3. 2023Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learningcited by 41
  4. 2024Securing Large Language Models: Threats, Vulnerabilities and Responsible Practicescited by 37
  5. 2023User Inference Attacks on Large Language Modelscited by 36
  6. 2023Split-and-Denoise: Protect large language model inference with local differential privacycited by 32
  7. 2024LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Modelscited by 32
  8. 2024HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversationscited by 31
  9. 2024PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restorationcited by 28
  10. 2025A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcarecited by 27
  11. 2024Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challengescited by 24
  12. 2023Low-Parameter Federated Learning with Large Language Modelscited by 23
  13. 2020Federated pretraining and fine tuning of BERT using clinical notes from multiple siloscited by 18
  14. 2023PrivateLoRA For Efficient Privacy Preserving LLMcited by 14
  15. 2024Enhancing Clinical Efficiency through LLM: Discharge Note Generation for Cardiac Patientscited by 14
  16. 2024PermLLM: Private Inference of Large Language Models within 3 Seconds under WANcited by 14
  17. 2021A Review of Anonymization for Healthcare Datacited by 12
  18. 2022Federated Multilingual Models for Medical Transcript Analysiscited by 11
  19. 2023Federated Learning of Medical Concepts Embedding using BEHRTcited by 11
  20. 2024Enhancing Large Language Models for Clinical Decision Support by Incorporating Clinical Practice Guidelinescited by 11
  21. 2024Personalized Wireless Federated Learning for Large Language Modelscited by 11
  22. 2024A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakagecited by 8
  23. 2024Privacy-Preserving Language Model Inference with Instance Obfuscationcited by 7
  24. 2025Mitigating Unintended Memorization with LoRA in Federated Learning for LLMscited by 7
  25. 2024MPC-Minimized Secure LLM Inferencecited by 6
  26. 2024Fine-Tuning LLMs for Reliable Medical Question-Answering Servicescited by 4
  27. 2024Transforming the Hybrid Cloud for Emerging AI Workloadscited by 4
  28. 2024PFID: Privacy First Inference Delegation Framework for LLMscited by 3
  29. 2024eFedLLM: Efficient LLM Inference Based on Federated Learningcited by 3
  30. 2025SHADE-AD: An LLM-Based Framework for Synthesizing Activity Data of Alzheimer's Patientscited by 2
  31. 2024Generative LLM Powered Conversational AI Application for Personalized Risk Assessment: A Case Study in COVID-19cited by 1
  32. 2024Large Language Model Federated Learning with Blockchain and Unlearning for Cross-Organizational Collaborationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Domain Adapted Large Language Models for Additive Manufacturingcited by 0
  2. 2026From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systemscited by 0
  3. 2026ARMED: Adaptive Retrieval-Augmented Medication Recommendationcited by 0