The doi above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
doi: 10.4121/21572601

Dekker, Florine; Erkin, Zekeriya; Conti, Mauro (2023): Dataset underlying the publication: Topology-Based Reconstruction Prevention for Decentralised Learning. Version 1. 4TU.ResearchData. dataset. https://doi.org/10.4121/21572601.v1

Dataset

• Artificial Intelligence and Image Processing
• Other Information and Computing Sciences
• Distributed Computing
• Information and Computing Sciences

composability, federated learning, graph theory, multi-party computation, reconstruction attack, statistical disclosure

CC BY-SA 4.0

RefWorks, BibTeX, Reference Manager, Endnote, DataCite, NLM, DC, CFF

by Florine W. Dekker , Zekeriya Erkin , Mauro Conti

MATLAB code to reproduce results presented in the paper "Topology-Based Reconstruction Prevention for Decentralised Learning".

This repository contains the source code of two experiments:

* `FeasibilitySim.zip` contains the source code of the experiments from Section 4. Its main script is `FeasibilitySim.m`.

* `PerformanceSim.zip` contains the source code of the experiments from Section 5.5. Its main script is `PerformanceSim.m`.

The main scripts in the respective archives contain more detailed usage instructions.

• 2023-12-18 first online, published, posted

4TU.ResearchData

MATLAB code

Topology-Based Reconstruction Prevention for Decentralised Learning

TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Intelligent Systems