SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning

2022/03/24 by Jahani-Nezhad, Tayyebeh, Maddah-Ali, Mohammad Ali, Li, Songze +1 · 4 citations
#Distributed #FOS: Computer and information sciences #Information Theory (cs.IT) #Machine Learning (cs.LG) #Parallel #and Cluster Computing (cs.DC)

paper · doi:10.48550/arxiv.2203.13060

Abstract

We propose SwiftAgg+, a novel secure aggregation protocol for federated learning systems, where a central server aggregates local models of N ∈ ℕ distributed users, each of size L ∈ ℕ, trained on their local data, in a privacy-preserving manner. SwiftAgg+ can significantly reduce the communication overheads without any compromise on security, and achieve optimal communication loads within diminishing gaps. Specifically, in presence of at most D=o(N) dropout users, SwiftAgg+ achieves a per-user communication load of (1+O((1)/(N)))L symbols and a server communication load of (1+O((1)/(N)))L symbols, with a worst-case information-theoretic security guarantee, against any subset of up to T=o(N) semi-honest users who may also collude with the curious server. Moreover, the proposed SwiftAgg+ allows for a flexible trade-off between communication loads and the number of active communication links. In particular, for T

Cited by

• Optimal Key Rates for Decentralized Secure Aggregation with Arbitrary Collusion and Heterogeneous Security Constraints
• The Capacity of Collusion-Resilient Decentralized Secure Aggregation with Groupwise Keys
• Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning
• Information-Theoretic Decentralized Secure Aggregation with Collusion Resilience

Related

• SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees
• Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning
• Asymptotically Optimal Secure Aggregation for Wireless Federated Learning with Multiple Servers
• FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
• Fluent: Round-efficient Secure Aggregation for Private Federated Learning