Privacy Preserving Vertical Federated Learning for Tree-based Models

Abstract

Federated learning (FL) is an emerging paradigm that enables multiple organizations to jointly train a model without revealing their private data to each other. This paper studies {\it vertical} federated learning, which tackles the scenarios where (i) collaborating organizations own data of the same set of users but with disjoint features, and (ii) only one organization holds the labels. We propose Pivot, a novel solution for privacy preserving vertical decision tree training and prediction, ensuring that no intermediate information is disclosed other than those the clients have agreed to release (i.e., the final tree model and the prediction output). Pivot does not rely on any trusted third party and provides protection against a semi-honest adversary that may compromise $m-1$ out of $m$ clients. We further identify two privacy leakages when the trained decision tree model is released in plaintext and propose an enhanced protocol to mitigate them. The proposed solution can also be extended to tree ensemble models, e.g., random forest (RF) and gradient boosting decision tree (GBDT) by treating single decision trees as building blocks. Theoretical and experimental analysis suggest that Pivot is efficient for the privacy achieved.

Proc. VLDB Endow. 13(11): 2090-2103 (2020)

References in corpus (7)

• XGBoost: A Scalable Tree Boosting System
• Learning Differentially Private Recurrent Language Models
• Analyzing Federated Learning through an Adversarial Lens
• SecureBoost: A Lossless Federated Learning Framework
• Privacy-Preserving Shortest Path Computation
• An Experimental Evaluation of Large Scale GBDT Systems
• Helen: Maliciously Secure Coopetitive Learning for Linear Models

Cited by in corpus (19)

• Vertical Federated Learning: Concepts, Advances and Challenges
• Feature Inference Attack on Model Predictions in Vertical Federated Learning
• Decentralized Federated Learning: A Survey on Security and Privacy
• BlindFL: Vertical Federated Machine Learning without Peeking into Your Data
• Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates
• Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks
• Cross-Silo Federated Learning for Multi-Tier Networks with Vertical and Horizontal Data Partitioning
• Feature Inference Attack on Shapley Values
• Differentially Private Vertical Federated Clustering
• NeurDB: An AI-powered Autonomous Data System
• Continual Horizontal Federated Learning for Heterogeneous Data
• EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third Party
• FedST: Secure Federated Shapelet Transformation for Time Series Classification
• ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems
• Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning
• Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligence
• Histogram-Based Federated XGBoost using Minimal Variance Sampling for Federated Tabular Data
• CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection
• Vertical Federated Image Segmentation