kth.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
Towards Decentralized Graph Learning
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.ORCID iD: 0000-0002-0223-8907
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: urn:nbn:se:kth:diva-327016ISBN: 978-91-8040-584-3 (print)OAI: oai:DiVA.org:kth-327016DiVA, id: diva2:1757592
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
List of papers
1. Gossip Learning: Off the Beaten Path
Open this publication in new window or tab >>Gossip Learning: Off the Beaten Path
2019 (English)Conference paper, Published paper (Refereed)
Abstract [en]

The growing computational demands of model training tasks and the increased privacy awareness of consumers call for the development of new techniques in the area of machine learning. Fully decentralized approaches have been proposed, but are still in early research stages. This study analyses gossip learning, one of these state-of-the-art decentralized machine learning protocols, which promises high scalability and privacy preservation, with the goal of assessing its applicability to realworld scenarios.

Previous research on gossip learning presents strong and often unrealistic assumptions on the distribution of the data, the communication speeds of the devices and the connectivity among them. Our results show that lifting these requirements can, in certain scenarios, lead to slow convergence of the protocol or even unfair bias in the produced models. This paper identifies the conditions in which gossip learning can and cannot be applied, and introduces extensions that mitigate some of its limitations.

National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-263863 (URN)10.1109/BigData47090.2019.9006216 (DOI)000554828701025 ()2-s2.0-85081314125 (Scopus ID)
Conference
2019 IEEE International Conference on Big Data (IEEE Big Data 2019), December 9-12, 2019, Los Angeles, CA, USA
Note

Accepted paper. QC 20191122

Available from: 2019-11-18 Created: 2019-11-18 Last updated: 2023-05-17Bibliographically approved
2. Federated Naive Bayes under Differential Privacy
Open this publication in new window or tab >>Federated Naive Bayes under Differential Privacy
2022 (English)In: Proceedings of the 19th International Conference on Security and Cryptography - SECRYPT / [ed] DiVimercati, SDC Samarati, P, Scitepress , 2022, p. 170-180Conference paper, Published paper (Refereed)
Abstract [en]

Growing privacy concerns regarding personal data disclosure are contrasting with the constant need of such information for data-driven applications. To address this issue, the combination of federated learning and differential privacy is now well-established in the domain of machine learning. These techniques allow to train deep neural networks without collecting the data and while preventing information leakage. However, there are many scenarios where simpler and more robust machine learning models are preferable. In this paper, we present a federated and differentially-private version of the Naive Bayes algorithm for classification. Our results show that, without data collection, the same performance of a centralized solution can be achieved on any dataset with only a slight increase in the privacy budget. Furthermore, if certain conditions are met, our federated solution can outperform a centralized approach.

Place, publisher, year, edition, pages
Scitepress, 2022
Keywords
Federated Learning, Naive Bayes, Differential Privacy
National Category
Other Computer and Information Science
Identifiers
urn:nbn:se:kth:diva-319088 (URN)10.5220/0011275300003283 (DOI)000853004900014 ()
Conference
19th International Conference on Security and Cryptography (SECRYPT), JUL 11-13, 2022, Lisbon, Portugal
Note

QC 20220926

Part of proceedings: ISBN 978-989-758-590-6

Available from: 2022-09-26 Created: 2022-09-26 Last updated: 2023-05-17Bibliographically approved
3. Towards a Realistic Decentralized Naive Bayeswith Differential Privacy
Open this publication in new window or tab >>Towards a Realistic Decentralized Naive Bayeswith Differential Privacy
(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
Federated learning, Gossip Learning, Differential privacy, Naive Bayes
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-325437 (URN)
Funder
EU, Horizon 2020, 813162
Note

QC 20230405

Available from: 2023-04-05 Created: 2023-04-05 Last updated: 2023-05-17Bibliographically approved
4. PDS2: A user-centered decentralized marketplace for privacy preserving data processing
Open this publication in new window or tab >>PDS2: A user-centered decentralized marketplace for privacy preserving data processing
Show others...
2021 (English)In: 2021 IEEE 37TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING WORKSHOPS (ICDEW 2021), Institute of Electrical and Electronics Engineers (IEEE) , 2021, p. 92-99Conference paper, Published paper (Refereed)
Abstract [en]

We envision PDS2, a decentralized data marketplace in which consumers submit their tasks to be run within the platform, on the data of willing providers. The goal of PDS2 is to ensure that users maintain full control on their data and do not compromise their privacy, while being rewarded for the value that their data generates. In order to achieve this, our marketplace architecture employs blockchain technology, privacypreserving computation and decentralized machine learning. We then compare different potential solutions and identify the Ethereum blockchain, trusted execution environments and gossip learning as the most suitable for the implementation of PDS2. We also discuss the main open challenges that are left to tackle and possible directions for future work.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2021
Series
IEEE International Conference on Data Engineering Workshop, ISSN 1943-2895
Keywords
iot, blockchain, machine learning, privacy
National Category
Computer Sciences Computer Systems
Identifiers
urn:nbn:se:kth:diva-300240 (URN)10.1109/ICDEW53142.2021.00024 (DOI)000681131300018 ()2-s2.0-85107689093 (Scopus ID)
Conference
37th IEEE International Conference on Data Engineering (IEEE ICDE), APR 19-22, 2021, ELECTR NETWORK
Note

Part of proceedings: ISBN 978-1-6654-4890-1, QC 20230117

Available from: 2021-08-30 Created: 2021-08-30 Last updated: 2023-05-17Bibliographically approved
5. Towards a decentralized infrastructure for data marketplaces: narrowing the gap between academia and industry
Open this publication in new window or tab >>Towards a decentralized infrastructure for data marketplaces: narrowing the gap between academia and industry
2022 (English)In: DE '22: Proceedings of the 1st International Workshop on Data Economy, New York, NY, USA: Association for Computing Machinery (ACM), 2022, p. 49-56Conference paper, Published paper (Refereed)
Abstract [en]

One big challenge for Industry 4.0 is leveraging the large amount of data that remain unused after collection. A variety of commercial data marketplaces have emerged in recent years to tackle this task. Despite their different business models and target markets, such marketplaces share a number of common issues that slow the growth of the industry, including data discovery, transparency, data privacy and data valuation. Many academic designs have been proposed to address these issues, yet most of them remain unimplemented, due to complexity or inefficiency.

We argue that these issues can be addressed with a combination of blockchain-based infrastructure, privacy-preserving computing and machine learning-based valuation metrics. Furthermore, we discuss key enabling technologies in each of these areas that are feasible to deploy at scale and could thus be implemented in real-world marketplaces in the near future. We select such technologies based on their current maturity and their industrial prominence.

Place, publisher, year, edition, pages
New York, NY, USA: Association for Computing Machinery (ACM), 2022
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-325815 (URN)
Conference
CoNEXT '22: The 18th International Conference on emerging Networking EXperiments and Technologies
Funder
EU, Horizon 2020, 813162
Note

QC 20230425

Available from: 2023-04-16 Created: 2023-04-16 Last updated: 2023-05-17Bibliographically approved
6. LiMNet: Early-Stage Detection of IoT Botnets with Lightweight Memory Networks
Open this publication in new window or tab >>LiMNet: Early-Stage Detection of IoT Botnets with Lightweight Memory Networks
Show others...
2021 (English)In: Computer Security – ESORICS 2021: 26th European Symposium on Research in Computer Security, Darmstadt, Germany, October 4–8, 2021, Proceedings, Part I / [ed] Elisa Bertino, Haya Shulman, Michael Waidner, Springer Nature , 2021Conference paper, Published paper (Refereed)
Abstract [en]

IoT devices have been growing exponentially in the last few years. This growth makes them an attractive target for attackers due to their low computational power and limited security features. Attackers use IoT botnets as an instrument to perform DDoS attacks which caused major disruptions of Internet services in the last decade. While many works have tackled the task of detecting botnet attacks, only a few have considered early-stage detection of these botnets during their propagation phase.

While previous approaches analyze each network packet individually to predict its maliciousness, we propose a novel deep learning model called LiMNet (Lightweight Memory Network), which uses an internal memory component to capture the behaviour of each IoT device over time. This memory incorporates both packet features and behaviour of the peer devices. With this information, LiMNet achieves almost maximum AUROC classification scores, between 98.8% and 99.7%, with a 14% improvement over state of the art. LiMNet is also lightweight, performing inference almost 8 times faster than previous approaches.

Place, publisher, year, edition, pages
Springer Nature, 2021
Series
Lecture Notes in Computer Science ; 12972
Keywords
IoT, botnet detection, machine learning
National Category
Communication Systems
Research subject
Computer Science; Telecommunication
Identifiers
urn:nbn:se:kth:diva-303027 (URN)10.1007/978-3-030-88418-5_29 (DOI)000772653800029 ()2-s2.0-85116855549 (Scopus ID)
Conference
Computer Security - ESORICS 2021 - 26th European Symposium on Research in Computer Security, Darmstadt, Germany, October 4-8, 2021
Funder
EU, Horizon 2020, 813162
Note

Part of proceedings: ISBN 978-3-030-88417-8

QC 20230117

Available from: 2021-10-05 Created: 2021-10-05 Last updated: 2023-12-11Bibliographically approved
7. Metasoma: Decentralized and CollaborativeEarly-Stage Detection of IoT Botnets
Open this publication in new window or tab >>Metasoma: Decentralized and CollaborativeEarly-Stage Detection of IoT Botnets
Show others...
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Early-stage detection of botnets during their spreadingphase, before any attack, is fundamental to IoT security.Recently introduced lightweight memory networks represent thestate of the art in this domain. However, they require a centralsystem to capture and analyze all traffic in the network, whichmay not always be feasible in real-world scenarios.In this paper, we introduce a decentralized and collaborativealternative, in which the IoT devices themselves are responsiblefor this task without any central observer or coordinator. Ourresults show that the performance of this novel approach iscompetitive with similar centralized solutions, despite the lackof a global view of the network at any participating device.We also provide an extensive analysis of the security limitationsof our fully-decentralized detection system. We identify thepotential exploits that an attacker may attempt to perform, assesstheir impact on the IoT network as well as propose and evaluateeffective countermeasures.

Keywords
Security and Privacy, Botnet Detection, Industrial IoT (IIoT), Device-to-Device Communication, Deep Learning
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-325436 (URN)
Funder
EU, Horizon 2020, 813162
Note

QC 20230405

Available from: 2023-04-05 Created: 2023-04-05 Last updated: 2023-05-17Bibliographically approved
8. Fully-Decentralized Training of GNNs using Layer-wise Self-Supervision
Open this publication in new window or tab >>Fully-Decentralized Training of GNNs using Layer-wise Self-Supervision
(English)Manuscript (preprint) (Other academic)
Abstract [en]

In existing literature, GNN training has been performed mostly in centralized, and sometimes federated, settings. In this work, we consider a fully-decentralized data-private scenario, where each node has limited knowledge of the surrounding graph. We propose the first architecture that enables GNN training in this fully-decentralized setting, by carefully combining several techniques, including decoupled learning, self-supervision and Gossip Learning. We implement two simulation tools to experimentally evaluate our solution. The results show that the proposed technique can be effectively used in scenarios where centralized or federated approaches are unfeasible or undesirable.

Keywords
Graph Neural Networks, Decentralized Learning, Self-Supervised Learning, Gossip Learning, Decoupled Learning
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-324971 (URN)
Funder
EU, Horizon 2020, 813162
Note

QC 20230322

Available from: 2023-03-22 Created: 2023-03-22 Last updated: 2023-05-17Bibliographically approved

Open Access in DiVA

summary(1608 kB)146 downloads
File information
File name SUMMARY01.pdfFile size 1608 kBChecksum SHA-512
bc669637be651450e26879078f57904829673447a10bbbe02f9de4e1043b958c1f7e52f7762fb907aa75c360c73aaefae3b47fc8ba6b1a78359f124fa9a2ac68
Type summaryMimetype application/pdf

Authority records

Giaretta, Lodovico

Search in DiVA

By author/editor
Giaretta, Lodovico
By organisation
Software and Computer systems, SCS
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
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

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1195 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