EUVIMEDEUVIMED entdecken
Open Access

Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems

Chun Joo Goh iD, Haoran Liu iD, Nethum Devendra iD, Khoa Nguyen Cao iD

JMIR Medical Informatics · 08.10.2026 · 14 · e101715

DOI: 10.2196/101715 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Medical Informatics, online erschienen am 08.10.2026. Verfasst von Chun Joo Goh und 3 weiteren Autor:innen. Beteiligte Einrichtung: Cao Lab for Medical AGI/ASI, Monash School of Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, Victoria, Austr…. Hauptthemen laut MEDLINE: Large Language Models, Computer Security. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this Viewpoint, we highlight the principal cybersecurity measures that should be implemented to facilitate safe and effective integration of large language models (LLMs) into health care and propose a conceptual, life cycle–based framework synthesizing evidence from security and clinical informatics literature. While LLMs offer significant potential for applications in clinical documentation, triage, and medical education, their deployment creates novel vulnerabilities that can compromise patient safety and data confidentiality. We argue that these vulnerabilities must be addressed across the entire deployment life cycle, with distinct threats arising before and after a model enters clinical use. Predeployment risks include data and model poisoning, where an LLM’s training data or core parameters are maliciously corrupted to embed biases or backdoors. After deployment, LLMs are susceptible to inference attacks, such as prompt injection and adversarial inputs, which can be used to manipulate model behavior and extract sensitive information. Standard performance benchmarks are often insufficient to detect these sophisticated attacks. Therefore, we argue that a proactive, multilayered security framework combining technical safeguards, rigorous governance, and human-in-the-loop oversight is essential for the safe and trustworthy adoption of LLMs in clinical practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsComputer SecurityHumans

Stichwörter der Autor:innen

AI deploymentclinical documentationcybersecurityhealth care deliveryhealth informaticsintegrationlarge language models

Autor:innen und Institutionen

  • Cao Lab for Medical AGI/ASI, Monash School of Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, Victoria, Australia.

ORCID-Profile: Chun Joo Goh, Haoran Liu, Nethum Devendra, Khoa Nguyen Cao

Zitieren

APA

Goh, C. J., Liu, H., Devendra, N., & Cao, K. N. (2026). Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems. JMIR Medical Informatics, 14, e101715. https://doi.org/10.2196/101715

Vancouver

Goh CJ, Liu H, Devendra N, Cao KN. Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems. JMIR Medical Informatics. 2026;14:e101715. doi:10.2196/101715

BibTeX
@article{Goh2026,
  author = {Goh, Chun Joo and Liu, Haoran and Devendra, Nethum and Cao, Khoa Nguyen},
  title = {Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems},
  journal = {JMIR Medical Informatics},
  year = {2026},
  volume = {14},
  pages = {e101715},
  doi = {10.2196/101715}
}
Kostenlos starten →