TU Darmstadt / ULB / TUbiblio

Enhancing Privacy via Hierarchical Federated Learning

Wainakh, Aidmar ; Sanchez Guinea, Alejandro ; Grube, Tim ; Mühlhäuser, Max (2020)
Enhancing Privacy via Hierarchical Federated Learning.
5th IEEE European Symposium on Security and Privacy Workshops (EuroS&PW 2020). Virtual Conference (07.-11.09.2020)
doi: 10.1109/EuroSPW51379.2020.00053
Conference or Workshop Item, Bibliographie

This is the latest version of this item.

Abstract

Federated learning suffers from several privacy-related issues that expose the participants to various threats. A number of these issues are aggravated by the centralized architecture of federated learning. In this paper, we discuss applying federated learning on a hierarchical architecture as a potential solution. We introduce the opportunities for more flexible decentralized control over the training process and its impact on the participants’ privacy. Furthermore, we investigate possibilities to enhance the efficiency and effectiveness of defense and verification methods.

Item Type: Conference or Workshop Item
Erschienen: 2020
Creators: Wainakh, Aidmar ; Sanchez Guinea, Alejandro ; Grube, Tim ; Mühlhäuser, Max
Type of entry: Bibliographie
Title: Enhancing Privacy via Hierarchical Federated Learning
Language: English
Date: 22 October 2020
Publisher: IEEE
Book Title: Proceedings : 5th IEEE European Symposium on Security and Privacy Workshops
Event Title: 5th IEEE European Symposium on Security and Privacy Workshops (EuroS&PW 2020)
Event Location: Virtual Conference
Event Dates: 07.-11.09.2020
DOI: 10.1109/EuroSPW51379.2020.00053
Corresponding Links:
Abstract:

Federated learning suffers from several privacy-related issues that expose the participants to various threats. A number of these issues are aggravated by the centralized architecture of federated learning. In this paper, we discuss applying federated learning on a hierarchical architecture as a potential solution. We introduce the opportunities for more flexible decentralized control over the training process and its impact on the participants’ privacy. Furthermore, we investigate possibilities to enhance the efficiency and effectiveness of defense and verification methods.

Additional Information:

published in: 6th International Workshop on Privacy Engineering (IWPE'20), part of the Conference

Divisions: 20 Department of Computer Science
20 Department of Computer Science > Telecooperation
Date Deposited: 09 Apr 2020 09:35
Last Modified: 16 Feb 2022 09:43
PPN:
Corresponding Links:
Export:
Suche nach Titel in: TUfind oder in Google

Available Versions of this Item

Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details