SeaFlame: Communication-Efficient Secure Aggregation for Federated Learning against Malicious Entities
Abstract: Secure aggregation is a popular solution to ensuring privacy for federated learning. However, when considering malicious participants in secure aggregation, it is difficult to achieve both privacy and high efficiency. Therefore, we propose SeaFlame, a communication-efficient secure aggregation protocol against malicious participants. Inspired by the state-of-the-art work, ELSA, SeaFlame also utilizes two non-colluding servers to ensure privacy against malicious entities and provide defenses against boosted gradients. Crucially, to improve communication efficiency, SeaFlame uses arithmetic sharing together with arithmetic-to-arithmetic share conversion to reduce client communication, and uses the random linear combination to reduce server communication. Security analysis proves that our SeaFlame guarantees privacy against malicious clients colluding with one malicious server. Experimental evaluation demonstrates that, compared to ELSA, SeaFlame optimizes communication by up to 10.5,.... https://tches.iacr.org/index.php/TCHES/article/view/12042
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
SeaFlame: Communication-Efficient Secure Aggregation for Federated Learning against Malicious Entities ; volume:2025 ; number:2 ; year:2025
IACR transactions on cryptographic hardware and embedded systems ; 2025, Heft 2 (2025)
- Urheber
-
Tang, Jinling
Xu, Haixia
Liao, Huimei
Zhou, Yinchang
- DOI
-
10.46586/tches.v2025.i2.69-93
- URN
-
urn:nbn:de:101:1-2503121801246.526179872478
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
15.08.2025, 07:23 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Tang, Jinling
- Xu, Haixia
- Liao, Huimei
- Zhou, Yinchang
Ähnliche Objekte (12)
Federated secure computing
Secure computation protocol of Chebyshev distance under the malicious model
PQSF: post-quantum secure privacy-preserving federated learning
Blockchain managed federated learning for a secure IoT framework
Secure malicious node detection in flying ad-hoc networks using enhanced AODV algorithm
Memristor‐Based Security Primitives Robust to Malicious Attacks for Highly Secure Neuromorphic Systems
An improving secure communication using multipath malicious avoidance routing protocol for underwater sensor network
Malicious Hypervisor Threat
Retraction Note: Blockchain managed federated learning for a secure IoT framework
Generalized global solar radiation forecasting model via cyber-secure deep federated learning
Martin Wong - Malicious Mischief
Æ-DIR - Authorized Entities Directory: from paranoid user management to secure system management
Federated secure computing
Secure computation protocol of Chebyshev distance under the malicious model
PQSF: post-quantum secure privacy-preserving federated learning
Blockchain managed federated learning for a secure IoT framework
Secure malicious node detection in flying ad-hoc networks using enhanced AODV algorithm
Memristor‐Based Security Primitives Robust to Malicious Attacks for Highly Secure Neuromorphic Systems
An improving secure communication using multipath malicious avoidance routing protocol for underwater sensor network
Malicious Hypervisor Threat
Retraction Note: Blockchain managed federated learning for a secure IoT framework
Generalized global solar radiation forecasting model via cyber-secure deep federated learning
Martin Wong - Malicious Mischief
Æ-DIR - Authorized Entities Directory: from paranoid user management to secure system management
Federated secure computing
Secure computation protocol of Chebyshev distance under the malicious model
PQSF: post-quantum secure privacy-preserving federated learning
Blockchain managed federated learning for a secure IoT framework
Secure malicious node detection in flying ad-hoc networks using enhanced AODV algorithm
Memristor‐Based Security Primitives Robust to Malicious Attacks for Highly Secure Neuromorphic Systems
An improving secure communication using multipath malicious avoidance routing protocol for underwater sensor network
Malicious Hypervisor Threat
Retraction Note: Blockchain managed federated learning for a secure IoT framework
Generalized global solar radiation forecasting model via cyber-secure deep federated learning
Martin Wong - Malicious Mischief