Fed-EALE: Efficient Authentication With Lightweight Encryption for Federated Learning in Vehicular Ad-Hoc Networks Using SSI

Abstract

In vehicular ad-hoc networks (VANET), federated learning enables vehicles to collaboratively train global models for intelligent transportation without sharing raw data. However, global model training faces various potential risks, such as identity leakage, privacy inference, and malicious attacks, due to the dynamic network structure and untrusted wireless communication of VANET. To address these issues, a robust authentication mechanism for federated learning must be achieved to ensure the trustworthiness of model parameters. In this paper, we propose an efficient and privacy-preserving authentication scheme with lightweight encryption for federated learning in VANET using self-sovereign identity (SSI), called Fed-EALE. Fed-EALE constructs Merkle pseudonym identity trees with the aid of decentralized identifiers. Vehicle participants use unlinkable pseudonyms to achieve privacy protection. Fed-EALE utilizes verifiable credentials and zero-knowledge proof to build the authentication protocol to ensure the authenticity and integrity of model parameters from anonymous vehicles. In addition, to accurately identify and eliminate malicious participants in anonymous communications, Fed-EALE can track and recover the real identities of malicious vehicles. We perform a security analysis of Fed-EALE. Performance evaluations indicate that Fed-EALE reduces authentication overhead by approximately 76% compared to state-of-the-art protocols, while maintaining high stability and scalability in VANET.