Federated Learning with Bayesian Differential Privacy

Abstract

We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy loss bounds. We adapt the Bayesian privacy accounting method to the federated setting and suggest multiple improvements for more efficient privacy budgeting at different levels. Our experiments show significant advantage over the state-of-the-art differential privacy bounds for federated learning on image classification tasks, including a medical application, bringing the privacy budget below 1 at the client level, and below 0.1 at the instance level. Lower amounts of noise also benefit the model accuracy and reduce the number of communication rounds.

Accepted at 2019 IEEE International Conference on Big Data (IEEE Big Data 2019). 10 pages, 2 figures, 4 tables. arXiv admin note: text overlap with arXiv:1901.09697

References in corpus (12)

• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Rényi Divergence and Kullback-Leibler Divergence
• Renyi Differential Privacy
• Towards Federated Learning at Scale: System Design
• Learning Differentially Private Recurrent Language Models
• Differentially Private Empirical Risk Minimization
• Differentially Private Federated Learning: A Client Level Perspective
• Scalable Private Learning with PATE
• Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences
• Generating Artificial Data for Private Deep Learning
• Rényi Differential Privacy Mechanisms for Posterior Sampling

Cited by in corpus (19)

• FedML: A Research Library and Benchmark for Federated Machine Learning
• A Systematic Literature Review on Federated Machine Learning: From A Software Engineering Perspective
• A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning
• Local Differential Privacy and Its Applications: A Comprehensive Survey
• Local Differential Privacy based Federated Learning for Internet of Things
• Wireless Federated Learning with Local Differential Privacy
• Hybrid Differentially Private Federated Learning on Vertically Partitioned Data
• FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning
• Low-Latency Federated Learning over Wireless Channels with Differential Privacy
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation
• A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations
• A Novel Privacy-Preserved Recommender System Framework based on Federated Learning
• Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
• A Vertical Federated Learning Method For Multi-Institutional Credit Scoring: MICS
• A Federated Data-Driven Evolutionary Algorithm
• New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design
• FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data
• FLBench: A Benchmark Suite for Federated Learning