NIPVS-FL: A Non-interactive Publicly Verifiable Secure Federated-Learning Scheme against Malicious Servers

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Federated learning (FL) enables decentralized data sources like mobile phones to joint training a neural network model without sharing the original data. However, shared local gradients make the privacy of local data in FL vulnerable. The aggregation server also may return incorrect results to clients due to unexpected error or the deliberately attack. In this work, we explore how to design a non-interactive and publicly verifiable aggregation scheme. The existing verifiable schemes are under semi-honest adversary model, in which the server is honest-but-curious but with additional power to counterfeit the aggregation result. We propose a scheme under stronger security model against malicious servers. The proposed scheme guarantees that as long as the two servers are non-colluding, even a malicious server cannot obtain input privacy of client. The malicious server will be detected by honest clients when it tries to tamper the result.

Original languageEnglish
Title of host publicationThird International Conference on Computer Communication and Network Security, CCNS 2022
EditorsChuanjun Zhao, Hilal Imane
PublisherSPIE
ISBN (Electronic)9781510660113
DOIs
StatePublished - 2022
Event3rd International Conference on Computer Communication and Network Security, CCNS 2022 - Hohhot, China
Duration: 15 Jul 202217 Jul 2022

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12453
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference3rd International Conference on Computer Communication and Network Security, CCNS 2022
Country/TerritoryChina
CityHohhot
Period15/07/2217/07/22

Keywords

  • Correct Exponentiation
  • Federated learning
  • Non-interactive
  • Publicly verifiable aggregation

Fingerprint

Dive into the research topics of 'NIPVS-FL: A Non-interactive Publicly Verifiable Secure Federated-Learning Scheme against Malicious Servers'. Together they form a unique fingerprint.

Cite this