Towards a Secure and Reliable Federated Learning using Blockchain - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Towards a Secure and Reliable Federated Learning using Blockchain

Résumé

Federated learning (FL) is a distributed machine learning (ML) technique that enables collaborative training in which devices perform learning using a local dataset while preserving their privacy. This technique ensures privacy, communication efficiency, and resource conservation. Despite these advantages, FL still suffers from several challenges related to reliability (i.e., unreliable participating devices in training), tractability (i.e., a large number of trained models), and anonymity. To address these issues, we propose a secure and trustworthy blockchain framework (SRB-FL) tailored to FL, which uses blockchain features to enable collaborative model training in a fully distributed and trustworthy manner. In particular, we design a secure FL based on the blockchain sharding that ensures data reliability, scalability, and trustworthiness. In addition, we introduce an incentive mechanism to improve the reliability of FL devices using subjective multi-weight logic. The results show that our proposed SRB- FL framework is efficient and scalable, making it a promising and suitable solution for federated learning.

Dates et versions

hal-03778457 , version 1 (15-09-2022)

Identifiants

Citer

Hajar Moudoud, Soumaya Cherkaoui, Lyes Khoukhi. Towards a Secure and Reliable Federated Learning using Blockchain. GLOBECOM 2021 - 2021 IEEE Global Communications Conference, Dec 2021, Madrid, France. pp.01-06, ⟨10.1109/GLOBECOM46510.2021.9685388⟩. ⟨hal-03778457⟩
20 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More