Digitala Vetenskapliga Arkivet

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
Towards a Realistic Decentralized Naive Bayeswith Differential Privacy
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.ORCID iD: 0000-0002-0223-8907
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.ORCID iD: 0000-0003-4516-7317
(English)Manuscript (preprint) (Other academic)
Abstract [en]

This is an extended version of our work in [16]. In this paper,we introduce two novel algorithms to collaboratively train Naive Bayesmodels across multiple private data sources: Federated Naive Bayes andGossip Naive Bayes. Instead of directly providing access to their data,the data owners compute local updates that are then aggregated to builda global model. In order to also prevent indirect privacy leaks from theupdates or from the final model, our algorithms protect the exchangedinformation with differential privacy. We experimentally evaluate ourproposed approaches, examining different scenarios and focusing on potentialreal-world issues, such as different data owner offering differentamounts of data or requesting different levels of privacy. Our results showthat both Federated and Gossip Naive Bayes achieve similar accuracy toa “vanilla” Naive Bayes while maintaining reasonable privacy guarantees,while being extremely robust to heterogeneous data owners.

Keywords [en]
Federated learning, Gossip Learning, Differential privacy, Naive Bayes
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-325437OAI: oai:DiVA.org:kth-325437DiVA, id: diva2:1749025
Funder
EU, Horizon 2020, 813162
Note

QC 20230405

Available from: 2023-04-05 Created: 2023-04-05 Last updated: 2023-05-17Bibliographically approved
In thesis
1. Towards Decentralized Graph Learning
Open this publication in new window or tab >>Towards Decentralized Graph Learning
2023 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Current Machine Learning (ML) approaches typically present either a centralized or federated architecture. However, these architectures cannot easily keep up with some of the challenges introduced by recent trends, such as the growth in the number of IoT devices, increasing awareness about the privacy and security implications of extensive data collection, and the rise of graph-structured data and Graph Representation Learning. Systems based on either direct data collection or Federated Learning contain centralized, privileged systems that may act as scalability bottlenecks and dangerous single points of failure, while requiring users to trust the privacy protections and security practices in place. The combination of these issues ultimately leads to data waste, as opportunities to extract insights from available data are missed and thus the full societal benefits of advanced data analytics and ML are not realized.

In this thesis, we argue for a paradigm shift towards a completely decentralized and trustless architecture for privacy-aware Graph Representation Learning, which employs Gossip Learning and other gossip-based peer-to-peer techniques to achieve high levels of scalability and resilience while reducing the risk of privacy leaks. We then identify and pursue three key research directions necessary to achieve our vision: lifting unrealistic assumptions on Gossip Learning, identifying and developing specific use cases that are enabled or improved by gossip-based decentralization, and overcoming the obstacles to the deployment of decentralized training and inference for Graph Representation Learning models.

 Based on these key directions, our contributions are as follows. First, we analyze the robustness of Gossip Learning when several unrealistic but often assumed conditions are lifted. Then, we exploit Gossip Learning and gossip-based peer-to-peer protocols more in general across three use cases: the collaborative training of differentially-private Naive Bayes classifiers across organizations holding sensitive user data; the construction of decentralized, privacy-preserving data marketplaces; and the development and decentralization of early-stage IoT botnet detection systems based on Graph Representation Learning. Finally, we introduce a general framework for the fully-decentralized training of Graph Neural Networks, overcoming the typical requirement of these models to access non-local information during training and inference.

 The combination of these contributions removes major roadblocks towards decentralized graph learning, and also opens a new research direction aimed at further developing and optimizing the fully-decentralized training of Graph Representation Learning models.

Abstract [sv]

Dagens metoder för maskininlärning (ML) har vanligtvis antingen en centraliserad eller federerad arkitektur. Dessa arkitekturer kan dock inte lätt hålla jämna steg med några av de utmaningar som introducerats av de senaste trenderna, som till exempel ökningen av antalet IoT-enheter, ökad medvetenhet om integritets- och säkerhetskonsekvenserna av omfattande datainsamling samt ökningen av grafstrukturerad data och Graph Representation Learning. System baserade på antingen direkt datainsamling eller federerad inlärning innehåller centraliserade, privilegierade system som kan vara flaskhalsar och riskerar bli kritiska sårbarhetspunkter. Samtidigt måste användarna lita på integritetsskyddet och säkerhetspraxis som finns. Kombinationen av dessa problem leder i slutändan till ett ineffektivt nyttjande av data, eftersom möjligheter att utvinna insikter från tillgänglig data inte utnyttjas och därmed inte realiserar de fulla samhällsnyttorna som är möjliga med avancerad dataanalys och ML.

I denna avhandling argumenterar vi för ett paradigmskifte mot en helt decentraliserad och tillitslös arkitektur för integritetsmedveten Graph Representation Learning, som använder Gossip Learning och andra gossip-baserade peer-to-peer-tekniker för att uppnå höga nivåer av skalbarhet och motståndskraft, samtidigt som den minskar risken för integritetsläckor. Vi identifierar och driver sedan tre viktiga forskningsinriktningar som är nödvändiga för att uppnå vår vision; att lyfta orealistiska antaganden om Gossip Learning, identifiera och utveckla specifika användningsfall som möjliggörs eller förbättras av gossip-baserad decentralisering, samt övervinna hindren för utplacering av decentraliserad utbildning och inferens för Graph Representation Learning modeller.

Baserat på dessa nyckelriktlinjer våra bidrag är följande. Först analyserar vi robustheten i Gossip Learning när flera orealistiska men ofta antagna villkor upphävs. Vi utnyttjar sedan Gossip Learning och gossip-baserade peer-to-peer-protokoll mer generellt i tre användningsfall: kollaborativ inlärning av differentiellt privata Naive Bayes-klassificerare över entiteter med känslig användardata; byggandet av decentraliserade datamarknadsplatser som bevarar integriteten; samt utveckling och decentralisering av IoT-botnätdetekterings\-system i ett tidigt skede baserade på Graph Representation Learning. Slutligen introducerar vi ett allmänt ramverk för helt decentraliserad utbildning av Graph Neural Networks, som eliminerar de typiska kraven för dessa modeller för att få tillgång till icke-lokal information under träning och inferens.

Kombinationen av dessa bidrag tar bort stora hinder mot decentraliserad grafinlärning, och öppnar också en ny forskningsriktning som syftar till att vidareutveckla och optimera den helt decentraliserade utbildningen av Graph Representation Learning modeller.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2023. p. vii, 59
Series
TRITA-EECS-AVL ; 2023:42
National Category
Computer Sciences
Research subject
Information and Communication Technology
Identifiers
urn:nbn:se:kth:diva-327016 (URN)978-91-8040-584-3 (ISBN)
Public defence
2023-06-09, Sal-C, Kistagången 16, Stockholm, 09:00 (English)
Opponent
Supervisors
Funder
EU, Horizon 2020, 813162
Note

QC 20230517

Available from: 2023-05-17 Created: 2023-05-17 Last updated: 2023-05-26Bibliographically approved

Open Access in DiVA

fulltext(2558 kB)147 downloads
File information
File name FULLTEXT01.pdfFile size 2558 kBChecksum SHA-512
93da6018a39cf26a798bd42102b93a20718fa3949cc21d589dee1f07b3cca9e9b1c1dc0f4d98dd03641a2b7ed5abcef4458f9653346b4f21e2627a92c6ad0a7d
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Giaretta, LodovicoMarchioro, ThomasMarkatos, EvangelosGirdzijauskas, Sarunas
By organisation
Software and Computer systems, SCS
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 147 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 230 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