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 (07.09.2020-11.09.2020)
doi: 10.1109/EuroSPW51379.2020.00053
Konferenzveröffentlichung, Bibliographie
Dies ist die neueste Version dieses Eintrags.
Kurzbeschreibung (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.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2020 |
| Autor(en): | Wainakh, Aidmar ; Sanchez Guinea, Alejandro ; Grube, Tim ; Mühlhäuser, Max |
| Art des Eintrags: | Bibliographie |
| Titel: | Enhancing Privacy via Hierarchical Federated Learning |
| Sprache: | Englisch |
| Publikationsjahr: | 22 Oktober 2020 |
| Verlag: | IEEE |
| Buchtitel: | Proceedings : 5th IEEE European Symposium on Security and Privacy Workshops |
| Veranstaltungstitel: | 5th IEEE European Symposium on Security and Privacy Workshops (EuroS&PW 2020) |
| Veranstaltungsort: | virtual Conference |
| Veranstaltungsdatum: | 07.09.2020-11.09.2020 |
| DOI: | 10.1109/EuroSPW51379.2020.00053 |
| Zugehörige Links: | |
| Kurzbeschreibung (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. |
| Zusätzliche Informationen: | published in: 6th International Workshop on Privacy Engineering (IWPE'20), part of the Conference |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Telekooperation |
| Hinterlegungsdatum: | 09 Apr 2020 09:35 |
| Letzte Änderung: | 22 Jul 2024 12:04 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
-
Enhancing Privacy via Hierarchical Federated Learning. (deposited 16 Feb 2022 09:51)
- Enhancing Privacy via Hierarchical Federated Learning. (deposited 09 Apr 2020 09:35) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum