THE ROLE OF FEDERATED LEARNING TECHNOLOGIES IN PROTECTING DATA PRIVACY

The growing use of big data, artificial intelligence and machine learning has made the protection of personal information a major concern. In conventional machine-learning systems, data are often centralised, increasing the risks of unauthorised access and disclosure. Federated learning offers an alternative by allowing models to be trained collaboratively while the original data remain on local devices or within institutional systems. This article examines its operating principles, contribution to data privacy, application areas and security limitations. It also considers differential privacy, secure aggregation and cryptographic techniques as complementary safeguards. The analysis shows that federated learning can reduce the need to transfer sensitive data, but does not guarantee privacy on its own; its effectiveness depends on an appropriately designed combination of technical, organisational and legal measures.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24423249
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

THE ROLE OF FEDERATED LEARNING TECHNOLOGIES IN PROTECTING DATA PRIVACY

Zinyet Revayet Huseynova
Zenodo (CERN European Organization for Nuclear Research)
Privacy-Preserving Technologies in Data
article

THE ROLE OF FEDERATED LEARNING TECHNOLOGIES IN PROTECTING DATA PRIVACY

Zinyet Revayet Huseynova
article en

Abstract

The growing use of big data, artificial intelligence and machine learning has made the protection of personal information a major concern. In conventional machine-learning systems, data are often centralised, increasing the risks of unauthorised access and disclosure. Federated learning offers an alternative by allowing models to be trained collaboratively while the original data remain on local devices or within institutional systems. This article examines its operating principles, contribution to data privacy, application areas and security limitations. It also considers differential privacy, secure aggregation and cryptographic techniques as complementary safeguards. The analysis shows that federated learning can reduce the need to transfer sensitive data, but does not guarantee privacy on its own; its effectiveness depends on an appropriately designed combination of technical, organisational and legal measures.

Zenodo (CERN European Organization for Nuclear Research)
Nakhchivan State University (AZ)
Privacy-Preserving Technologies in Data
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon