Journal article · 2026 · Open access

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

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

JMIR Medical Informatics, 14, e101715 · Published 23 September 2026 · DOI 10.2196/101715

Open full textCite this paper

In brief

“Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems” is a 2026 journal article by Chun Joo Goh and 3 co-authors, published in JMIR Medical Informatics. OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at JMIR Medical Informatics.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.08
References
27
Authors
4

Abstract

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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

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

MLA 9

Goh, Chun Joo, et al. “Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems.” JMIR Medical Informatics, vol. 14, 2026, p. e101715. https://doi.org/10.2196/101715.

Chicago

Goh, Chun Joo, Haoran Liu, Nethum Devendra, and Khoa Nguyen Cao. 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.

Harvard

Goh, C. J. et al. (2026) ‘Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems’, JMIR Medical Informatics, 14, p. e101715. doi:10.2196/101715.

IEEE

C. J. Goh, H. Liu, N. Devendra, and K. N. Cao, “Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems,” JMIR Medical Informatics, vol. 14, p. e101715, 2026, doi: 10.2196/101715.

BibTeX

@article{goh2026cybersecurity,
  title     = {{Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems}},
  author    = {Goh, Chun Joo and Liu, Haoran and Devendra, Nethum and Cao, Khoa Nguyen},
  journal   = {JMIR Medical Informatics},
  year      = {2026},
  volume    = {14},
  pages     = {e101715},
  doi       = {10.2196/101715},
  url       = {https://doi.org/10.2196/101715}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • large language models
  • cybersecurity
  • health care
  • data poisoning
  • model poisoning
  • backdoors
  • prompt injection
  • adversarial attacks

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

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

How many times has this paper been cited?

1 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at JMIR Medical Informatics: sign in and open the full text from this page.

Who wrote this paper?

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

What is the DOI of this paper?

10.2196/101715, permanently at https://doi.org/10.2196/101715. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.