Author
Listed:
- Answer Mushedhe
- Onuh Matthew Ijiga
Abstract
The increasing migration of healthcare information systems to cloud computing environments has intensified concerns regarding database backup integrity, ransomware attacks, unauthorized data modification, backup corruption, and operational disruptions affecting the availability and recoverability of sensitive patient records. Conventional backup protection mechanisms, including checksum-based validation, scheduled backup verification, rule-based intrusion detection, and static disaster recovery procedures, provide essential safeguards but may fail to recognize sophisticated integrity attacks, identify compromised recovery points, or optimize restoration under rapidly changing threat conditions. This paper proposes BackupIntegrity, a novel artificial intelligence-enabled framework integrating adaptive anomaly detection, cryptographic integrity verification, predictive backup reliability assessment, and risk-aware automated recovery for healthcare databases hosted in cloud environments. The proposed framework introduces the Backup Integrity-Aware Adaptive Recovery Algorithm (BIARA), which combines a Temporal Transformer Network (TTN), an Isolation Forest (IF), a Gated Recurrent Unit (GRU), and a Multi-Objective Recovery Optimization (MORO) mechanism within a unified protection and restoration architecture. The Temporal Transformer captures long-range dependencies in backup activity sequences, while the Isolation Forest identifies abnormal backup access, modification, and encryption patterns. The GRU estimates backup failure probabilities and degradation trends, whereas the optimization component selects verified recovery points by jointly minimizing recovery time, potential data loss, residual compromise risk, and operational recovery costs. Cryptographic SHA-256 verification, authenticated backup manifests, immutable storage policies, and recovery-point dependency analysis provide additional safeguards against backup manipulation and contaminated restoration. The proposed system will be evaluated using a controlled cloud-based healthcare database testbed incorporating representative electronic health record transactions, incremental and full backup operations, simulated ransomware incidents, unauthorized backup modifications, storage failures, and recovery scenarios. Its performance will be compared with conventional checksum-based backup verification, rule-based security monitoring, standalone Isolation Forest, Long ShortTerm Memory (LSTM), and XGBoost-based detection and recovery approaches. Experimental evaluation will examine detection accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve (AUC-ROC), falsepositive rate, backup verification latency, recovery time objective (RTO), recovery point objective (RPO), data restoration success rate, and computational overhead. Comparative performance graphs, ROC curves, recovery-time distributions, reliability trajectories, and multi-objective optimization plots will be used to determine whether BIARA provides statistically significant improvements over the benchmark approaches. The anticipated contribution is a reproducible, integrity-aware cloud recovery architecture capable of strengthening ransomware resilience, identifying trustworthy restoration points, reducing recovery uncertainty, and supporting the continuity, confidentiality, and availability of critical healthcare information systems.
Suggested Citation
Answer Mushedhe & Onuh Matthew Ijiga, 2026.
"BackupIntegrity: AI-Enabled Protection and Recovery of Healthcare Database Backups in Cloud Environments,"
International Journal of Innovative Science and Research Technology (IJISRT), IJISRT Publication, vol. 11(10), pages 551-574, October.
Handle:
RePEc:cvr:ijisrt:2026:10:ijisrt26oct623
DOI: https://doi.org/10.38124/ijisrt/26Oct623
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:cvr:ijisrt:2026:10:ijisrt26oct623. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Rahul Goyel (email available below). General contact details of provider: https://www.ijisrt.com/ .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.