Secure XGBoost Documentation

Secure XGBoost is a secure gradient boosting library based off the popular XGBoost project. In addition to offering the efficiency, flexibility, and portability that vanilla XGBoost does to solve a variety of problems, Secure XGBoost enables secure collaborative learning by leveraging hardware enclaves and oblivious algorithms. This project allows multiple parties to each share their sensitive data to perform joint computation without revealing the contents of the data.

This project is currently under development as part of the broader Multiparty Collaboration and Coopetition effort by the UC Berkeley RISE Lab.

We welcome contributions to our work here.

Contents

• Installation Guide
• Tutorials
  • Secure XGBoost in Jupyter
• Secure XGBoost Parameters
• Python package
  • Python Package Introduction
  • Python API Reference