SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914256184672256 |
|---|---|
| author | Tahera, Mohoshin Ara Sidhu, Karamveer Singh Dass, Shuvalaxmi Saha, Sajal |
| author_facet | Tahera, Mohoshin Ara Sidhu, Karamveer Singh Dass, Shuvalaxmi Saha, Sajal |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10004 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations Tahera, Mohoshin Ara Sidhu, Karamveer Singh Dass, Shuvalaxmi Saha, Sajal Cryptography and Security Machine Learning 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. |
| title | SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2601.10004 |