Skip to content
Open access

An Efficient and Secure Framework for Enhancing Data and Model Security in Healthcare AI

Aug 2026 · International Journal of Computer Science and Engineering · Vol 14, pp. 13-21 · 0 citations

TL;DR

A dual-layer security architecture that combines AES-256 data encryption, homomorphic encryption (HE) for model protection, role-based access control (RBAC) with multi-factor authentication (MFA) and the digital watermarking for model ownership verification is proposed.

Abstract

The Artificial Intelligence (AI) enabled healthcare systems are require simultaneous defense of complex patient data and of the trained models. The paper proposes a dual-layer security architecture that combines AES-256 data encryption, homomorphic encryption (HE) for model protection, role-based access control (RBAC) with multi-factor authentication (MFA) and the digital watermarking for model ownership verification. The outline is evaluated on the MIMIC-III clinical dataset using a feedforward neural network for healthcare prediction. The experimental results show a test accuracy of 92.53%, data encryption and decryption times of 0.144s and 0.109s, model-level encryption and decryption times of 0.0019s and 0.0002s with a watermark tamper resistance of 99.95% under simulated adversarial attack. Compared with three recent baseline frameworks, the proposed approach achieves the highest tamper resistance and the fastest encryption or decryption operations the outperforms the layered cryptographic and access-control mechanisms as embedded into an AIML pipeline without the compromising low latency requirements of real world clinical deployment.

Read PDF

Similar papers

Conference Open access Oct 2026

MultiLevelGAN: A Secure Adversarial Framework for Image Encryption and Protected Communications

With digital communication networks, cloud platforms and connected devices expanding rapidly, data security has never been as important. Cryptography techniques which for so long proved to be effective now face increasing opposition as attackers advance and computing power continues to accelerate in its abilities. Scie...

Ranjith Bhat, Rajashree Nambiar · 0 citations
Open access Sep 2026

Secure Medical Image Transmission based on Confidence-Adaptive Chaos Encryption (CACE) over Healthcare IoT Networks

Secure transmission of medical images over IoT networks requires strong encryption and maintenance of diagnostic value. To overcome this, this paper proposes an adaptive approach called Confidence-Adaptive Chaos Encryption (CACE) that is based on the SVM classifier confidence for choosing the strength of encryption for...

Zainab N. Abdulhameed, H. Hatem, E. Yahia · 0 citations
Conference Open access Sep 2026

A Deception-Based Framework for Brute-Force-Resistant Medical Data Security

There are difficulties in securing patient records in digital healthcare settings where patient medical reports and diagnostic images have to be sent through possibly untrusted networks. Single-layer approaches for security may have some flaws due to vulnerability to brute force attacks on keys. We introduce a hybrid a...

B. Srujana, K. Madhuri, K. Shailaja et al. · 0 citations
Open access Nov 2026

Enhanced cloud security via optimal fire hawks XOR and probabilistic super learning

Every visit to a doctor leaves a record of diagnoses, prescriptions and test results, and patients rely on those records staying safe for years to come. Despite its widespread use and vast range of services, cloud computing presents privacy and security concerns, thus international organizations are developing cloud se...

Anupama Cg, Arun C, Ratnakumari Neerukonda · 0 citations
Open access Oct 2026

Secure Medical Data Hiding Using DWT, QPSO, and Lightweight Encryption

With the ever-increasing demand for secure transmission and storage of medical records in a healthcare system, quick and effective data protection techniques are required. In this paper, a new approach of using Speck-Cipher, Discrete Wavelet Transform (DWT), and Quantum-based Particle Swarm Optimization (QPSO) is propo...

A. Badr, M. Talal, Amal Sufiuh Ajrash et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.