BlindFL: Vertical Federated Machine Learning without Peeking into Your Data

Abstract

Due to the rising concerns on privacy protection, how to build machine learning (ML) models over different data sources with security guarantees is gaining more popularity. Vertical federated learning (VFL) describes such a case where ML models are built upon the private data of different participated parties that own disjoint features for the same set of instances, which fits many real-world collaborative tasks. Nevertheless, we find that existing solutions for VFL either support limited kinds of input features or suffer from potential data leakage during the federated execution. To this end, this paper aims to investigate both the functionality and security of ML modes in the VFL scenario. To be specific, we introduce BlindFL, a novel framework for VFL training and inference. First, to address the functionality of VFL models, we propose the federated source layers to unite the data from different parties. Various kinds of features can be supported efficiently by the federated source layers, including dense, sparse, numerical, and categorical features. Second, we carefully analyze the security during the federated execution and formalize the privacy requirements. Based on the analysis, we devise secure and accurate algorithm protocols, and further prove the security guarantees under the ideal-real simulation paradigm. Extensive experiments show that BlindFL supports diverse datasets and models efficiently whilst achieves robust privacy guarantees.

SIGMOD 2022

References in corpus (13)

• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Federated Machine Learning: Concept and Applications
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• Deep Learning Recommendation Model for Personalization and Recommendation Systems
• CryptoDL: Deep Neural Networks over Encrypted Data
• Privacy Preserving Vertical Federated Learning for Tree-based Models
• Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator
• HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework
• OpenBox: A Generalized Black-box Optimization Service
• PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm
• SEALion: a Framework for Neural Network Inference on Encrypted Data
• Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning
• Vertical Federated Learning without Revealing Intersection Membership

Cited by in corpus (8)

• Vertical Federated Learning: Concepts, Advances and Challenges
• Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates
• Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks
• Practical Differentially Private and Byzantine-resilient Federated Learning
• A Distributed Privacy Preserving Model for the Detection of Alzheimer's Disease
• FedST: Secure Federated Shapelet Transformation for Time Series Classification
• Horizontal Federated Computer Vision
• Vertical Federated Image Segmentation