TY - JOUR

T1 - SwiftAgg+

T2 - Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning

AU - Jahani-Nezhad, Tayyebeh

AU - Maddah-Ali, Mohammad Ali

AU - Li, Songze

AU - Caire, Giuseppe

N1 - Publisher Copyright:
© 1983-2012 IEEE.

PY - 2023/4/1

Y1 - 2023/4/1

N2 - We propose SwiftAgg+, a novel secure aggregation protocol for federated learning systems, where a central server aggregates local models of $N \in \mathbb {N}$ distributed users, each of size $L \in \mathbb {N}$ , 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 $\left({1+\mathcal {O}\left({\frac {1}{N}}\right)}\right)L$ symbols and a server communication load of $\left({1+\mathcal {O}\left({\frac {1}{N}}\right)}\right)L$ 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 $T< N-D$ and for any $K\in \mathbb {N}$ , SwiftAgg+ can achieve the server communication load of $\left({1+\frac {T}{K}}\right)L$ symbols, and per-user communication load of up to $\left({1+\frac {T+D}{K}}\right)L$ symbols, where the number of pair-wise active connections in the network is $\frac {N}{2}(K+T+D+1)$.

AB - We propose SwiftAgg+, a novel secure aggregation protocol for federated learning systems, where a central server aggregates local models of $N \in \mathbb {N}$ distributed users, each of size $L \in \mathbb {N}$ , 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 $\left({1+\mathcal {O}\left({\frac {1}{N}}\right)}\right)L$ symbols and a server communication load of $\left({1+\mathcal {O}\left({\frac {1}{N}}\right)}\right)L$ 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 $T< N-D$ and for any $K\in \mathbb {N}$ , SwiftAgg+ can achieve the server communication load of $\left({1+\frac {T}{K}}\right)L$ symbols, and per-user communication load of up to $\left({1+\frac {T+D}{K}}\right)L$ symbols, where the number of pair-wise active connections in the network is $\frac {N}{2}(K+T+D+1)$.

KW - Federated learning

KW - dropout resiliency

KW - optimal communication load

KW - secret sharing

KW - secure aggregation

UR - http://www.scopus.com/inward/record.url?scp=85149472701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85149472701&partnerID=8YFLogxK

U2 - 10.1109/JSAC.2023.3242702

DO - 10.1109/JSAC.2023.3242702

M3 - Article

AN - SCOPUS:85149472701

SN - 0733-8716

VL - 41

SP - 977

EP - 989

JO - IEEE Journal on Selected Areas in Communications

JF - IEEE Journal on Selected Areas in Communications

IS - 4

ER -