Information Theoretic Secure Aggregation with Uncoded Groupwise Keys

04/24/2022
by   Kai Wan, et al.
0

Secure aggregation, which is a core component of federated learning, aggregates locally trained models from distributed users at a central server. The "secure" nature of such aggregation consists of the fact that no information about the local users' data must be leaked to the server except the aggregated local models. In order to guarantee security, some keys may be shared among the users (this is referred to as the key sharing phase). After the key sharing phase, each user masks its trained model which is then sent to the server (this is referred to as the model aggregation phase). This paper follows the information theoretic secure aggregation problem originally formulated by Zhao and Sun, with the objective to characterize the minimum communication cost from the K users in the model aggregation phase. Due to user dropouts, the server may not receive all messages from the users. A secure aggregation schemes should tolerate the dropouts of at most K-U users, where U is a system parameter. The optimal communication cost is characterized by Zhao and Sun, but with the assumption that the keys stored by the users could be any random variables with arbitrary dependency. On the motivation that uncoded groupwise keys are more convenient to be shared and could be used in large range of applications besides federated learning, in this paper we add one constraint into the above problem, that the key variables are mutually independent and each key is shared by a group of at most S users, where S is another system parameter. To the best of our knowledge, all existing secure aggregation schemes assign coded keys to the users. We show that if S > K - U, a new secure aggregation scheme with uncoded groupwise keys can achieve the same optimal communication cost as the best scheme with coded keys; if S ≤ K - U, uncoded groupwise key sharing is strictly sub-optimal.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/24/2022

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

We propose SwiftAgg+, a novel secure aggregation protocol for federated ...
research
01/19/2021

Information Theoretic Secure Aggregation with User Dropouts

In the robust secure aggregation problem, a server wishes to learn and o...
research
01/17/2019

Private Authentication: Optimal Information Theoretic Schemes

The main security service in the connected world of cyber physical syste...
research
07/25/2023

Secure Aggregation with an Oblivious Server

Secure aggregation usually aims at securely computing the sum of the inp...
research
05/17/2022

Secure Summation: Capacity Region, Groupwise Key, and Feasibility

The secure summation problem is considered, where K users, each holds an...
research
10/28/2022

Machine Unlearning of Federated Clusters

Federated clustering is an unsupervised learning problem that arises in ...

Please sign up or login with your details

Forgot password? Click here to reset