CoChat

Trustworthy Federated Learning via Blockchain

Open access
Yang, Zhanpeng, Shi, Yuanming, Zhou, Yong, Wang, Zixin, Yang, Kai · 2023 · IEEE Internet of Things Journal
Cited by 122

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Abstract

The safety-critical scenarios of artificial intelligence (AI), such as autonomous driving, Internet of Things, smart healthcare, etc., have raised critical requirements of trustworthy AI to guarantee the privacy and security with reliable decisions. As a nascent branch for trustworthy AI, federated learning (FL) has been regarded as a promising privacy preserving framework for training a global AI model over collaborative devices. However, security challenges still exist in the FL framework, e.g., Byzantine attacks from malicious devices, and model tampering attacks from malicious server, which will degrade or destroy the accuracy of trained global AI model. In this article, we shall propose a decentralized blockchain-based FL (B-FL) architecture by using a secure global aggregation algorithm to resist malicious devices, and deploying a practical Byzantine fault tolerance consensus protocol with high effectiveness and low energy consumption among multiple edge servers to prevent model tampering from the malicious server. However, to implement B-FL system at the network edge, multiple rounds of cross-validation in blockchain consensus protocol will induce long training latency. We thus formulate a network optimization problem that jointly considers bandwidth and power allocation for the minimization of long-term average training latency consisting of progressive learning rounds. We further propose to transform the network optimization problem as a Markov decision process and leverage the deep reinforcement learning (DRL)-based algorithm to provide high system performance with low computational complexity. Simulation results demonstrate that B-FL can resist malicious attacks from edge devices and servers, and the training latency of B-FL can be significantly reduced by the DRL-based algorithm compared with the baseline algorithms.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jiot.2022.3201117

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 29

  1. 10.1109/MWC.001.2000345 · DOI
  2. 10.1109/JSAC.2021.3118401 · DOI · Paper page
  3. 10.23919/JCIN.2022.9815197 · doi:10.23919/jcin.2022.9815197
  4. 10.1109/TCOMM.2021.3124961 · DOI
  5. Blanchard, Machine learning with adversaries: Byzantine tolerant gradient descent, 118
  6. 10.1109/TWC.2019.2956519 · DOI · Paper page
  7. 10.1109/JIOT.2018.2871706 · DOI · Paper page
  8. 10.1109/MCOM.2018.1701095 · DOI · Paper page
  9. 10.1109/COMST.2020.2969706 · DOI · Paper page
  10. Wang, 2021, Blockchain-based federated learning: A comprehensive survey, arXiv:2110.02182 · arXiv
  11. 10.1109/MNET.001.1900658 · DOI · Paper page
  12. 10.1109/MCOM.2019.1900271 · DOI · Paper page
  13. 10.1016/c2020-0-00624-9 · doi:10.1016/c2020-0-00624-9
  14. 10.23919/JCIN.2022.9815195 · DOI · Paper page
  15. 10.1109/IPCCC51483.2021.9679419 · DOI
  16. 10.1109/JSAC.2020.3036971 · DOI · Paper page
  17. Yang, 2020, Delay minimization for federated learning over wireless communication networks, arXiv:2007.03462 · arXiv
  18. Castro, Practical Byzantine fault tolerance, 99, 173
  19. 10.1109/TWC.2020.3021177 · DOI · Paper page
  20. 10.1109/TCCN.2020.3027696 · DOI
  21. 10.1109/TII.2020.3017668 · DOI · Paper page
  22. 10.1109/tpds.2021.3138848 · DOI · Paper page
  23. 10.1109/JSAC.2022.3213344 · DOI · Paper page
  24. 10.1109/JIOT.2020.3032544 · DOI · Paper page
  25. 10.1109/JIOT.2019.2940820 · DOI · Paper page
  26. 10.1109/jiot.2020.3026354 · DOI
  27. 10.1109/TPDS.2021.3096076 · DOI · Paper page
  28. 10.1109/ICCWorkshops50388.2021.9473694 · DOI
  29. 10.1109/TCOMM.2021.3135540 · DOI

Cited by

See all 122

Metadata

Authors
Yang, Z., Shi, Y., Zhou, Y., Wang, Z., & Yang, K.
Venue
IEEE Internet of Things Journal
Published
2023-01-01
Volume
10
Issue
1
Pages
92-109
ISSN
  • 2327-4662 (ISSN-L)
  • 2372-2541
OpenAlex
W4293211913
Cited by
122
References
29
FWCI
8.16
Type
journal article
Language
en
Open access
green
Funders
  • Shanghai Rising-Star Program (22QA1406100)
  • Natural Science Foundation of Shanghai (21ZR1442700)
  • National Natural Science Foundation of China (U20A20159, 62001294)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.