Cloud-based Federated Boosting for Mobile Crowdsensing

TL;DR

This paper introduces FedXGB, a privacy-preserving federated learning architecture for extreme gradient boosting in mobile crowdsensing, achieving high accuracy with strong security guarantees.

Contribution

It proposes a novel secret sharing-based federated boosting framework that preserves model privacy against GAN-based attacks in mobile crowdsensing.

Findings

Less than 1% accuracy loss compared to original XGBoost

Secure against honest-but-curious adversaries

Effective and efficient in privacy-preserving classification

Abstract

The application of federated extreme gradient boosting to mobile crowdsensing apps brings several benefits, in particular high performance on efficiency and classification. However, it also brings a new challenge for data and model privacy protection. Besides it being vulnerable to Generative Adversarial Network (GAN) based user data reconstruction attack, there is not the existing architecture that considers how to preserve model privacy. In this paper, we propose a secret sharing based federated learning architecture FedXGB to achieve the privacy-preserving extreme gradient boosting for mobile crowdsensing. Specifically, we first build a secure classification and regression tree (CART) of XGBoost using secret sharing. Then, we propose a secure prediction protocol to protect the model privacy of XGBoost in mobile crowdsensing. We conduct a comprehensive theoretical analysis and extensive experiments to evaluate the security, effectiveness, and efficiency of FedXGB. The results indicate that FedXGB is secure against the honest-but-curious adversaries and attains less than 1% accuracy loss compared with the original XGBoost model.