Publikationer från Malmö universitet
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Leveraging Federated Learning & Blockchain to counter Adversarial Attacks in Incremental Learning
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).ORCID-id: 0000-0003-4071-4596
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).ORCID-id: 0000-0003-0546-072X
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).ORCID-id: 0000-0002-9471-8405
Visa övriga samt affilieringar
2020 (Engelska)Ingår i: IoT '20 Companion: 10th International Conference on the Internet of Things Companion, ACM Digital Library, 2020, s. 1-5, artikel-id 2Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Whereas data labelling in IoT applications is costly, it is also time consuming to train a supervised Machine Learning (ML) algorithm. Hence, a human oracle is required to gradually annotate the data patterns at run-time to improve the models’ learning behavior, through an active learning strategy in form of User Feedback Process (UFP). Consequently, it is worth to note that during UFP there may exist malicious content that may subject the learning model to be vulnerable to adversarial attacks, more so, manipulative attacks. We argue in this position paper, that there are instances during incremental learning, where the local data model may present wrong output, if retraining is done using data that has already been subjected to adversarial attack. We propose a Distributed Interactive Secure Federated Learning (DISFL) framework that utilizes UFP in the edge and fog node, that subsequently increases the amount of labelled personal local data for the ML model during incremental training. Furthermore, the DISFL framework addresses data privacy by leveraging federated learning, where only the model's knowledge is moved to a global unit, herein referred to as Collective Intelligence Node (CIN). During incremental learning, this would then allow the creation of an immutable chain of data that has to be trained, which in its entirety is tamper-free while increasing trust between parties. With a degree of certainty, this approach counters adversarial manipulation during incremental learning in active learning context at the same time strengthens data privacy, while reducing the computation costs.

Ort, förlag, år, upplaga, sidor
ACM Digital Library, 2020. s. 1-5, artikel-id 2
Nyckelord [no]
Federated learning, adversarial, blockchain, privacy, incremental training
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:mau:diva-48196DOI: 10.1145/3423423.3423425ISI: 001062649200002Scopus ID: 2-s2.0-85117542476ISBN: 9781450388207 (digital)OAI: oai:DiVA.org:mau-48196DiVA, id: diva2:1620287
Konferens
10th International Conference on the Internet of Things Companion, October 6-9, 2020, Malmö Sweden
Forskningsfinansiär
KK-stiftelsenTillgänglig från: 2021-12-15 Skapad: 2021-12-15 Senast uppdaterad: 2023-12-13Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopusJournal website

Person

Kebande, Victor R.Alawadi, SadiBugeja, JosephPersson, Jan A.Olsson, Carl Magnus

Sök vidare i DiVA

Av författaren/redaktören
Kebande, Victor R.Alawadi, SadiBugeja, JosephPersson, Jan A.Olsson, Carl Magnus
Av organisationen
Institutionen för datavetenskap och medieteknik (DVMT)
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 33 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf