HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning

Abstract

Federated learning has emerged as a promising approach for collaborative and privacy-preserving learning. Participants in a federated learning process cooperatively train a model by exchanging model parameters instead of the actual training data, which they might want to keep private. However, parameter interaction and the resulting model still might disclose information about the training data used. To address these privacy concerns, several approaches have been proposed based on differential privacy and secure multiparty computation (SMC), among others. They often result in large communication overhead and slow training time. In this paper, we propose HybridAlpha, an approach for privacy-preserving federated learning employing an SMC protocol based on functional encryption. This protocol is simple, efficient and resilient to participants dropping out. We evaluate our approach regarding the training time and data volume exchanged using a federated learning process to train a CNN on the MNIST data set. Evaluation against existing crypto-based SMC solutions shows that HybridAlpha can reduce the training time by 68% and data transfer volume by 92% on average while providing the same model performance and privacy guarantees as the existing solutions.

arXiv comment12 pages, AISec 2019

References in corpus (9)

• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• A generic framework for privacy preserving deep learning
• Scalable Private Learning with PATE
• Extremal Mechanisms for Local Differential Privacy
• SecureBoost: A Lossless Federated Learning Framework
• Machine Learning with Membership Privacy using Adversarial Regularization

Cited by in corpus (32)

• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• FedML: A Research Library and Benchmark for Federated Machine Learning
• Decentralized Federated Learning: A Survey on Security and Privacy
• A Systematic Literature Review on Federated Machine Learning: From A Software Engineering Perspective
• IBM Federated Learning: an Enterprise Framework White Paper V0.1
• Privacy-Preserving Machine Learning: Methods, Challenges and Directions
• TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning
• Boosting Privately: Privacy-Preserving Federated Extreme Boosting for Mobile Crowdsensing
• Communication Efficiency in Federated Learning: Achievements and Challenges
• Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations
• The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
• FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
• Mitigating Bias in Federated Learning
• Fog Computing as Privacy Enabler
• AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization
• Blockchain-based Transparency Framework for Privacy Preserving Third-party Services
• A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
• FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Data
• NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets
• Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
• Federated Learning on Non-IID Data: A Survey
• Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm
• PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy
• Privacy-preserving Decentralized Aggregation for Federated Learning
• Distributed Additive Encryption and Quantization for Privacy Preserving Federated Deep Learning
• Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning
• Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning
• FLRA: A Reference Architecture for Federated Learning Systems
• Flatee: Federated Learning Across Trusted Execution Environments
• Revisiting Secure Computation Using Functional Encryption: Opportunities and Research Directions
• Adaptive Federated Learning with Functional Encryption: A Comparison of Classical and Quantum-safe Options
• MYSTIKO : : Cloud-Mediated, Private, Federated Gradient Descent