PFilter: Privacy-Aware and Secure Data Filtering at the Edge for Distributed Edge Analytics - Artificial Intelligence Applications and Innovations
Conference Papers Year : 2021

PFilter: Privacy-Aware and Secure Data Filtering at the Edge for Distributed Edge Analytics

Annanda Rath
  • Function : Author
  • PersonId : 1167881
Anna Hristoskova
  • Function : Author
  • PersonId : 1167839
Sarah Klein
  • Function : Author
  • PersonId : 1167882

Abstract

This paper is presenting a conceptual mechanism for light-weight privacy-aware and secure data access control and filtering. This mechanism can be deployed at an edge node in order to assure that all data coming in and going out of it is properly protected and filtered. Goal is to keep private data locally and limit its exposure to outside entities (e.g., Cloud backend, external application or other edge nodes) while preserving the performance and security requirements for edge analytics. The data filtering at the edge node is done in a way that it is not possible for outside entities to identify end-devices and the data associated with them.
Fichier principal
Vignette du fichier
517424_1_En_25_Chapter.pdf (281.74 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03789025 , version 1 (27-09-2022)

Licence

Identifiers

Cite

Annanda Rath, Anna Hristoskova, Sarah Klein. PFilter: Privacy-Aware and Secure Data Filtering at the Edge for Distributed Edge Analytics. 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2021, Hersonissos, Crete, Greece. pp.305-310, ⟨10.1007/978-3-030-79157-5_25⟩. ⟨hal-03789025⟩
37 View
17 Download

Altmetric

Share

More