Journal article · 2026 · Open access
Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies
Journal of Medical Internet Research, 28, e87969 · Published 23 January 2026 · DOI 10.2196/87969
In brief
“Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies” is a 2026 journal article by Farhad Abtahi and 3 co-authors, published in Journal of Medical Internet Research. OpenAlex counts 39 citations as of 17 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Journal of Medical Internet Research.
- Citations
- 39
- Most cited in
- 2026 (39)
- Field-weighted impact
- 44.64
- References
- 49
- Authors
- 4
Abstract
BACKGROUND: Health care artificial intelligence (AI) systems are increasingly integrated into clinical workflows, yet remain vulnerable to data-poisoning attacks. A small number of manipulated training samples can compromise AI models used for diagnosis, documentation, and resource allocation. Existing privacy regulations, including the Health Insurance Portability and Accountability Act and the General Data Protection Regulation, may inadvertently complicate anomaly detection and cross-institutional auditing, thereby limiting visibility into adversarial activity. OBJECTIVE: This study provides a comprehensive threat analysis of data poisoning vulnerabilities across major health care AI architectures. The goals are to (1) identify attack surfaces in clinical AI systems, (2) evaluate the feasibility and detectability of poisoning attacks analytically modeled in prior security research, and (3) propose a multilayered defense framework appropriate for health care settings. METHODS: We synthesized empirical findings from 41 key security studies published between 2019 and 2025 and integrated them into an analytical threat-modeling framework specific to health care. We constructed 8 hypothetical yet technically grounded attack scenarios across 4 categories: (1) architecture-specific attacks on convolutional neural networks, large language models, and reinforcement learning agents (scenario A); (2) infrastructure exploitation in federated learning and clinical documentation pipelines (scenario B); (3) poisoning of critical resource allocation systems (scenario C); and (4) supply chain attacks affecting commercial foundation models (scenario D). Scenarios were aligned with realistic insider-access threat models and current clinical deployment practices. RESULTS: Multiple empirical studies demonstrate that attackers with access to as few as 100-500 poisoned samples can compromise health care AI systems, with attack success rates typically ≥60%. Critically, attack success depends on the absolute number of poisoned samples rather than their proportion of the training corpus, a finding that fundamentally challenges assumptions that larger datasets provide inherent protection. We estimate that detection delays commonly range from 6 to 12 months and may extend to years in distributed or privacy-constrained environments. Analytical scenarios highlight that (1) routine insider access creates numerous injection points across health care data infrastructure, (2) federated learning amplifies risks by obscuring attribution, and (3) supply chain compromises can simultaneously affect dozens to hundreds of institutions. Privacy regulations further complicate cross-patient correlation and model audit processes, substantially delaying the detection of subtle poisoning campaigns. CONCLUSIONS: Health care AI systems face significant security challenges that current regulatory frameworks and validation practices do not adequately address. We propose a multilayered defense strategy that combines ensemble disagreement monitoring, adversarial testing, privacy-preserving yet auditable mechanisms, and strengthened governance requirements. Ensuring patient safety may require a shift from opaque, high-performance models toward more interpretable and constraint-driven architectures…
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Abtahi, F., Seoane, F., Pau, I., & Vega-Barbas, M. (2026). Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies. Journal of Medical Internet Research, 28, e87969. https://doi.org/10.2196/87969
MLA 9
Abtahi, Farhad, et al. “Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies.” Journal of Medical Internet Research, vol. 28, 2026, p. e87969. https://doi.org/10.2196/87969.
Chicago
Abtahi, Farhad, Fernando Seoane, Iván Pau, and Mario Vega-Barbas. 2026. “Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies.” Journal of Medical Internet Research 28: e87969. https://doi.org/10.2196/87969.
Harvard
Abtahi, F. et al. (2026) ‘Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies’, Journal of Medical Internet Research, 28, p. e87969. doi:10.2196/87969.
IEEE
F. Abtahi, F. Seoane, I. Pau, and M. Vega-Barbas, “Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies,” Journal of Medical Internet Research, vol. 28, p. e87969, 2026, doi: 10.2196/87969.
BibTeX
@article{abtahi2026data,
title = {{Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies}},
author = {Abtahi, Farhad and Seoane, Fernando and Pau, Iván and Vega-Barbas, Mario},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e87969},
doi = {10.2196/87969},
url = {https://doi.org/10.2196/87969}
}
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
- data poisoning
- threat modeling
- federated learning security
- large language models
- reinforcement learning agents
- supply chain attacks
- foundation models
- resource allocation systems
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Abtahi, F., Seoane, F., Pau, I., & Vega-Barbas, M. (2026). Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies. Journal of Medical Internet Research, 28, e87969. https://doi.org/10.2196/87969
How many times has this paper been cited?
39 times, according to OpenAlex on 17 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 Journal of Medical Internet Research: sign in and open the PDF from this page.
Who wrote this paper?
Farhad Abtahi, Fernando Seoane, Iván Pau, Mario Vega-Barbas.
What is the DOI of this paper?
10.2196/87969, permanently at https://doi.org/10.2196/87969. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 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.