Resilient Cloud Architectures with AI Agents for Enhancing Cybersecurity in Health Information Systems
Bibliographic record
Abstract
The growing adoption of electronic health records (EHRs), Internet of Medical Things (IoMT) devices and cloud-hosted platforms have not only improved healthcare efficiency but also expanded the cybersecurity vulnerabilities by expanding the attack surface. This highlights the need for resilient, adaptive and robust security frameworks in cloud environments. This study presents a resilient cloud architecture with AI agents for enhancing cybersecurity in healthcare information systems. The framework integrates an Isolation Forest (iForest) as a first-layer anomaly detector and XGBoost classifier for supervised intrusion detection, forming a two-layered defense mechanism. The iForest module isolates abnormal traffic patterns and filters potential intrusions, while the XGBoost classifier performs fine-grained classification of retained traffic flows. Together, this hybrid design minimizes false alarms, reduces misclassifications and ensures that benign and attack traffic are accurately distinguished in real time. Using the CIC IoMT 2024 dataset, the hybrid framework achieved an accuracy of 98.48%, a precision of 99.23%, a recall of 98.85%, and an F1-score of 99.04%, outperforming standalone baselines. ROC analysis further confirmed the framework’s superior detection capability with an AUC of 0.99. The framework’s layered adaptability and scalability make it well-suited for securing sensitive medical data and ensuring the continuity of healthcare services.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".