FedComm: A Privacy-Enhanced and Efficient Authentication Protocol for Federated Learning in Vehicular Ad-Hoc Networks

Basit Öğe Kaydı
dc.authoridWANG, WEI/0000-0002-5974-1589
dc.authoridLi, Tao/0000-0003-1697-8022
dc.authoridLiu, jiqiang/0000-0003-1147-4327
dc.authoridYuan, Xiaohan/0000-0002-8489-4018
dc.contributor.authorYuan, Xiaohan
dc.contributor.authorLiu, Jiqiang
dc.contributor.authorWang, Bin
dc.contributor.authorWang, Wei
dc.contributor.authorWang, Bin
dc.contributor.authorLi, Tao
dc.contributor.authorMa, Xiaobo
dc.date.accessioned2024-05-19T14:46:18Z
dc.date.available2024-05-19T14:46:18Z
dc.date.issued2024
dc.departmentİstinye Üniversitesien_US
dc.description.abstractIn vehicular ad-hoc networks (VANET), federated learning enables vehicles to collaboratively train a global model for intelligent transportation without sharing their local data. However, due to dynamic network structure and unreliable wireless communication of VANET, various potential risks (e.g., identity privacy leakage, data privacy inference, model integrity compromise, and data manipulation) undermine the trustworthiness of intermediate model parameters necessary for building the global model. While existing cryptography techniques and differential privacy provide provable security paradigms, the practicality of secure federated learning in VANET is hindered in terms of training efficiency and model performance. Therefore, developing a secure and efficient federated learning in VANET remains a challenge. In this work, we propose a privacy-enhanced and efficient authentication protocol for federated learning in VANET, called FedComm. Unlike existing solutions, FedComm addresses the above challenge through user anonymity. First, FedComm enables vehicles to participate in training with unlinkable pseudonyms, ensuring both privacy preservation and efficient collaboration. Second, FedComm incorporates an efficient authentication protocol to guarantee the authenticity and integrity of model parameters originated from anonymous vehicles. Finally, FedComm accurately identifies and completely eliminates malicious vehicles in anonymous communication. Security analysis and verification with ProVerif demonstrate that FedComm enhances privacy and reliability of intermediate model parameters. Experimental results show that FedComm reduces the overhead of proof generation and verification by 67.38% and 67.39%, respectively, compared with the state-of-the-art authentication protocols used in federated learning.en_US
dc.description.sponsorshipFundamental Research Funds for the Central Universities of Chinaen_US
dc.description.sponsorshipNo Statement Availableen_US
dc.identifier.doi10.1109/TIFS.2023.3324747
dc.identifier.endpage792en_US
dc.identifier.issn1556-6013
dc.identifier.issn1556-6021
dc.identifier.scopus2-s2.0-85174799297en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage777en_US
dc.identifier.urihttps://doi.org10.1109/TIFS.2023.3324747
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5490
dc.identifier.volume19en_US
dc.identifier.wosWOS:001119528500004en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIeee-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Transactions on Information Forensics and Securityen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectPrivacyen_US
dc.subjectProtocolsen_US
dc.subjectVehicular Ad Hoc Networksen_US
dc.subjectAuthenticationen_US
dc.subjectData Modelsen_US
dc.subjectTrainingen_US
dc.subjectFederated Learningen_US
dc.subjectPrivacy Preservationen_US
dc.subjectFederated Learningen_US
dc.subjectCredible Accessen_US
dc.subjectAnonymous Auditen_US
dc.titleFedComm: A Privacy-Enhanced and Efficient Authentication Protocol for Federated Learning in Vehicular Ad-Hoc Networksen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu