Information-Theoretic Secure Aggregation in Decentralized Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xiang, Li, Zhou, Li, Shuangyang, Wan, Kai, Ng, Derrick Wing Kwan, Caire, Giuseppe
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918401028390912
author Zhang, Xiang
Li, Zhou
Li, Shuangyang
Wan, Kai
Ng, Derrick Wing Kwan
Caire, Giuseppe
author_facet Zhang, Xiang
Li, Zhou
Li, Shuangyang
Wan, Kai
Ng, Derrick Wing Kwan
Caire, Giuseppe
contents Motivated by the increasing demand for data security in decentralized federated learning (FL) and stochastic optimization, we formulate and investigate the problem of information-theoretic \emph{decentralized secure aggregation} (DSA). Specifically, we consider a network of $K$ interconnected users, each holding a private input, representing, for example, local model updates in FL, who aim to simultaneously compute the sum of all inputs while satisfying the security requirement that no user, even when colluding with up to $T$ others, learns anything beyond the intended sum. We characterize the optimal rate region, which specifies the minimum achievable communication and secret key rates for DSA. In particular, we show that to securely compute one bit of the desired input sum, each user must (i) transmit at least one bit to all other users, (ii) hold at least one bit of secret key, and (iii) all users must collectively hold no fewer than $K - 1$ independent key bits. Our result establishes the fundamental performance limits of DSA and offers insights into the design of provably secure and communication-efficient protocols for distributed learning systems.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17970
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Information-Theoretic Secure Aggregation in Decentralized Networks
Zhang, Xiang
Li, Zhou
Li, Shuangyang
Wan, Kai
Ng, Derrick Wing Kwan
Caire, Giuseppe
Information Theory
Motivated by the increasing demand for data security in decentralized federated learning (FL) and stochastic optimization, we formulate and investigate the problem of information-theoretic \emph{decentralized secure aggregation} (DSA). Specifically, we consider a network of $K$ interconnected users, each holding a private input, representing, for example, local model updates in FL, who aim to simultaneously compute the sum of all inputs while satisfying the security requirement that no user, even when colluding with up to $T$ others, learns anything beyond the intended sum. We characterize the optimal rate region, which specifies the minimum achievable communication and secret key rates for DSA. In particular, we show that to securely compute one bit of the desired input sum, each user must (i) transmit at least one bit to all other users, (ii) hold at least one bit of secret key, and (iii) all users must collectively hold no fewer than $K - 1$ independent key bits. Our result establishes the fundamental performance limits of DSA and offers insights into the design of provably secure and communication-efficient protocols for distributed learning systems.
title Information-Theoretic Secure Aggregation in Decentralized Networks
topic Information Theory
url https://arxiv.org/abs/2601.17970