Boosting Privately: Privacy-Preserving Federated Extreme Boosting for Mobile Crowdsensing

Abstract

Recently, Google and other 24 institutions proposed a series of open challenges towards federated learning (FL), which include application expansion and homomorphic encryption (HE). The former aims to expand the applicable machine learning models of FL. The latter focuses on who holds the secret key when applying HE to FL. For the naive HE scheme, the server is set to master the secret key. Such a setting causes a serious problem that if the server does not conduct aggregation before decryption, a chance is left for the server to access the user's update. Inspired by the two challenges, we propose FedXGB, a federated extreme gradient boosting (XGBoost) scheme supporting forced aggregation. FedXGB mainly achieves the following two breakthroughs. First, FedXGB involves a new HE based secure aggregation scheme for FL. By combining the advantages of secret sharing and homomorphic encryption, the algorithm can solve the second challenge mentioned above, and is robust to the user dropout. Then, FedXGB extends FL to a new machine learning model by applying the secure aggregation scheme to the classification and regression tree building of XGBoost. Moreover, we conduct a comprehensive theoretical analysis and extensive experiments to evaluate the security, effectiveness, and efficiency of FedXGB. The results indicate that FedXGB achieves less than 1% accuracy loss compared with the original XGBoost, and can provide about 23.9% runtime and 33.3% communication reduction for HE based model update aggregation of FL.

References in corpus (8)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Learning Differentially Private Recurrent Language Models
• HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning
• SecureBoost: A Lossless Federated Learning Framework
• Analyzing gender inequality through large-scale Facebook advertising data
• A Hybrid Approach to Privacy-Preserving Federated Learning
• Entity Resolution and Federated Learning get a Federated Resolution
• A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression

Cited by in corpus (15)

• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Stratified cross-validation for unbiased and privacy-preserving federated learning
• Large-Scale Secure XGB for Vertical Federated Learning
• An Efficient Learning Framework For Federated XGBoost Using Secret Sharing And Distributed Optimization
• Practical Federated Gradient Boosting Decision Trees
• Privacy-Preserving Asynchronous Federated Learning Algorithms for Multi-Party Vertically Collaborative Learning
• When Crowdsensing Meets Federated Learning: Privacy-Preserving Mobile Crowdsensing System
• Adaptive Histogram-Based Gradient Boosted Trees for Federated Learning
• A Genetic Algorithm-Based Support Vector Machine Approach for Intelligent Usability Assessment of m-Learning Applications
• Privacy-Preserving XGBoost Inference
• Revocable Federated Learning: A Benchmark of Federated Forest
• Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Histogram-Based Federated XGBoost using Minimal Variance Sampling for Federated Tabular Data