Cloud-based Federated Boosting for Mobile Crowdsensing
This work addresses privacy vulnerabilities in mobile crowdsensing apps, offering a solution for scenarios where data and model confidentiality are critical, though it appears incremental as it builds on existing federated learning and XGBoost methods.
The paper tackles the challenge of data and model privacy protection in federated extreme gradient boosting for mobile crowdsensing by proposing FedXGB, a secret sharing-based architecture that achieves less than 1% accuracy loss compared to the original model while securing against honest-but-curious adversaries.
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.