Vijayalakshmi

Histogram-Optimized CKKS Encrypted Federated XGBoost for Privacy-Preserving Healthcare Analytics

This repository contains the dataset associated with the manuscript entitled “Histogram-Optimized CKKS Encrypted Federated XGBoost for Privacy-Preserving Healthcare Analytics.” The experiments use two datasets: A fully reproducible synthetic EHR dataset. The publicly available UCI Heart Disease dataset ( Janosi, A., Steinbrunn, W., Pfisterer, M., & Detrano, R. (1989). Heart Disease [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C52P4X.) The synthetic dataset is not intended to represent a real patient cohort. It is provided as a controlled benchmark for evaluating the proposed encrypted federated-learning architecture under reproducible non-IID conditions.