Efficient Sparse Secure Aggregation for Federated Learning

Abstract

Federated Learning enables one to jointly train a machine learning model across distributed clients holding sensitive datasets. In real-world settings, this approach is hindered by expensive communication and privacy concerns. Both of these challenges have already been addressed individually, resulting in competing optimisations. In this article, we tackle them simultaneously for one of the first times. More precisely, we adapt compression-based federated techniques to additive secret sharing, leading to an efficient secure aggregation protocol, with an adaptable security level. We prove its privacy against malicious adversaries and its correctness in the semi-honest setting. Experiments on deep convolutional networks demonstrate that our secure protocol achieves high accuracy with low communication costs. Compared to prior works on secure aggregation, our protocol has a lower communication and computation costs for a similar accuracy.

References in corpus (4)

• Protection Against Reconstruction and Its Applications in Private Federated Learning
• Error Feedback Fixes SignSGD and other Gradient Compression Schemes
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

Cited by in corpus (3)

• Efficient Dropout-resilient Aggregation for Privacy-preserving Machine Learning
• ScionFL: Efficient and Robust Secure Quantized Aggregation
• Federated learning with differential privacy and an untrusted aggregator