Gehlhar, Till ; Marx, Felix ; Schneider, Thomas ; Suresh, Ajith ; Wehrle, Tobias ; Yalame, Hossein (2023)
SAFEFL: MPC-friendly Framework for Private and Robust Federated Learning.
6th Deep Learning Security and Privacy Workshop (DLSP 2023). San Francisco, USA (25.05.2023)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Federated learning (FL) has gained widespread popularity in a variety of industries due to its ability to locally train models on devices while preserving privacy. However, FL systems are susceptible to i) privacy inference attacks and ii) poisoning attacks, which can compromise the system by corrupt actors. Despite a significant amount of work being done to tackle these attacks individually, the combination of these two attacks has received limited attention in the research community.
To address this gap, we introduce SAFEFL, a secure multiparty computation (MPC)-based framework designed to assess the efficacy of FL techniques in addressing both privacy inference and poisoning attacks. The heart of the SAFEFL framework is a communicator interface that enables PyTorch-based implementations to utilize the well established MP-SPDZ framework, which implements various MPC protocols. The goal of SAFEFL is to facilitate the development of more efficient FL systems that can effectively address privacy inference and poisoning attacks.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Gehlhar, Till ; Marx, Felix ; Schneider, Thomas ; Suresh, Ajith ; Wehrle, Tobias ; Yalame, Hossein |
| Art des Eintrags: | Bibliographie |
| Titel: | SAFEFL: MPC-friendly Framework for Private and Robust Federated Learning |
| Sprache: | Englisch |
| Publikationsjahr: | 25 Mai 2023 |
| Veranstaltungstitel: | 6th Deep Learning Security and Privacy Workshop (DLSP 2023) |
| Veranstaltungsort: | San Francisco, USA |
| Veranstaltungsdatum: | 25.05.2023 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | Federated learning (FL) has gained widespread popularity in a variety of industries due to its ability to locally train models on devices while preserving privacy. However, FL systems are susceptible to i) privacy inference attacks and ii) poisoning attacks, which can compromise the system by corrupt actors. Despite a significant amount of work being done to tackle these attacks individually, the combination of these two attacks has received limited attention in the research community. To address this gap, we introduce SAFEFL, a secure multiparty computation (MPC)-based framework designed to assess the efficacy of FL techniques in addressing both privacy inference and poisoning attacks. The heart of the SAFEFL framework is a communicator interface that enables PyTorch-based implementations to utilize the well established MP-SPDZ framework, which implements various MPC protocols. The goal of SAFEFL is to facilitate the development of more efficient FL systems that can effectively address privacy inference and poisoning attacks. |
| Freie Schlagworte: | Engineering, E4, Cryptography and Privacy Engineering (ENCRYPTO) CYSEC, GRK Privacy&Trust for Mobile Users (Project A.1) |
| Zusätzliche Informationen: | Part of the 44th IEEE Symposium on Security and Privacy, 22.-25.05.2023 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Praktische Kryptographie und Privatheit 20 Fachbereich Informatik > Kryptographische Protokolle DFG-Sonderforschungsbereiche (inkl. Transregio) DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 2050 Privacy and Trust for Mobile Users Profilbereiche Profilbereiche > Cybersicherheit (CYSEC) DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1119: CROSSING – Kryptographiebasierte Sicherheitslösungen als Grundlage für Vertrauen in heutigen und zukünftigen IT-Systemen |
| Hinterlegungsdatum: | 10 Jul 2023 08:41 |
| Letzte Änderung: | 10 Jul 2023 08:41 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum