https://www.mdu.se/

mdu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
SparSFA: Towards robust and communication-efficient peer-to-peer federated learning
RISE Research Institutes of Sweden, Kista, Sweden.ORCID iD: 0000-0002-2772-4661
Imperial College London, London, United Kingdom.ORCID iD: 0000-0001-6093-5922
IBM Research Europe, Dublin, Ireland.ORCID iD: 0000-0002-8250-9681
RISE Research Institutes of Sweden, Kista, Sweden.
Show others and affiliations
2023 (English)In: Computers & security (Print), ISSN 0167-4048, E-ISSN 1872-6208, Vol. 129, article id 103182Article in journal (Refereed) Published
Abstract [en]

Federated Learning (FL) has emerged as a powerful paradigm to train collaborative machine learning (ML) models, preserving the privacy of the participants’ datasets. However, standard FL approaches present some limitations that can hinder their applicability in some applications. Thus, the need of a server or aggregator to orchestrate the learning process may not be possible in scenarios with limited connectivity, as in some IoT applications, and offer less flexibility to personalize the ML models for the different participants. To sidestep these limitations, peer-to-peer FL (P2PFL) provides more flexibility, allowing participants to train their own models in collaboration with their neighbors. However, given the huge number of parameters of typical Deep Neural Network architectures, the communication burden can also be very high. On the other side, it has been shown that standard aggregation schemes for FL are very brittle against data and model poisoning attacks. In this paper, we propose SparSFA, an algorithm for P2PFL capable of reducing the communication costs. We show that our method outperforms competing sparsification methods in P2P scenarios, speeding the convergence and enhancing the stability during training. SparSFA also includes a mechanism to mitigate poisoning attacks for each participant in any random network topology. Our empirical evaluation on real datasets for intrusion detection in IoT, considering both balanced and imbalanced-dataset scenarios, shows that SparSFA is robust to different indiscriminate poisoning attacks launched by one or multiple adversaries, outperforming other robust aggregation methods whilst reducing the communication costs through sparsification.

Place, publisher, year, edition, pages
2023. Vol. 129, article id 103182
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-64229DOI: 10.1016/j.cose.2023.103182ISI: 000961304800001Scopus ID: 2-s2.0-85151480655OAI: oai:DiVA.org:mdh-64229DiVA, id: diva2:1796198
Funder
European CommissionAvailable from: 2023-09-11 Created: 2023-09-11 Last updated: 2023-10-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Raza, Shahid

Search in DiVA

By author/editor
Wang, HanMuñoz-González, LuisHameed, Muhammad ZaidRaza, Shahid
In the same journal
Computers & security (Print)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 19 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf