Byzantine-Resilient Secure Federated Learning

Secure federated learning is a privacy-preserving framework to improve machine learning models by training over large volumes of data collected by mobile users. This is achieved through an iterative process where, at each iteration, users update a global model using their local datasets. Each user t...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal on selected areas in communications 2021-07, Vol.39 (7), p.2168-2181
Main Authors: So, Jinhyun, Guler, Basak, Avestimehr, A. Salman
Format: Article
Language:English
Subjects:
Agglomeration
Byzantine-resilience
Convergence
Data analysis
Datasets
distributed training in mobile networks
Federated learning
Iterative methods
Machine learning
Masks
Outliers (statistics)
Privacy
privacy-preserving machine learning
Resilience
Servers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Secure federated learning is a privacy-preserving framework to improve machine learning models by training over large volumes of data collected by mobile users. This is achieved through an iterative process where, at each iteration, users update a global model using their local datasets. Each user then masks its local update via random keys, and the masked models are aggregated at a central server to compute the global model for the next iteration. As the local updates are protected by random masks, the server cannot observe their true values. This presents a major challenge for the resilience of the model against adversarial (Byzantine) users, who can manipulate the global model by modifying their local updates or datasets. Towards addressing this challenge, this paper presents the first single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning. BREA is based on an integrated stochastic quantization, verifiable outlier detection, and secure model aggregation approach to guarantee Byzantine-resilience, privacy, and convergence simultaneously. We provide theoretical convergence and privacy guarantees and characterize the fundamental trade-offs in terms of the network size, user dropouts, and privacy protection. Our experiments demonstrate convergence in the presence of Byzantine users, and comparable accuracy to conventional federated learning benchmarks.
ISSN:0733-8716
1558-0008
DOI:10.1109/JSAC.2020.3041404