Samplable Anonymous Aggregation for Private Federated Data Analysis

07/27/2023

∙

We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Our first contribution is to propose a simple primitive that allows for efficient implementation of several commonly used algorithms, and allows for privacy accounting that is close to that in the central setting without requiring the strong trust assumptions it entails. Second, we propose a system architecture that implements this primitive and perform a security analysis of the proposed system.

READ FULL TEXT

Samplable Anonymous Aggregation for Private Federated Data Analysis

Private Federated Statistics in an Interactive Setting

Scalable and Differentially Private Distributed Aggregation in the Shuffled Model

Private Aggregation in Wireless Federated Learning with Heterogeneous Clusters

Faithful Edge Federated Learning: Scalability and Privacy

Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation

Private Federated Learning with Autotuned Compression

Data Privacy in Trigger-Action IoT Systems

Samplable Anonymous Aggregation for Private Federated Data Analysis

Related Research

Private Federated Statistics in an Interactive Setting

Scalable and Differentially Private Distributed Aggregation in the Shuffled Model

Private Aggregation in Wireless Federated Learning with Heterogeneous Clusters

Faithful Edge Federated Learning: Scalability and Privacy

Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation

Private Federated Learning with Autotuned Compression

Data Privacy in Trigger-Action IoT Systems