Securing AI-as-a-service platform through blockchain and smart-contracts

Nadar, Ali; Härri, Jérôme
VTC-Spring 2026, IEEE 103rd Vehicular Technology Conference, 9-12 June 2026, Nice, France

Vehicular AI-as-a-Service (AIaaS) enables connected vehicles to request and receive machine learning models over lightweight publish/subscribe connectivity like MQTT. However, this raises critical concerns about security, integrity, and accountability. This paper proposes a blockchain-enabled extension to our AIaaS platform that records model requests and deliveries on an immutable ledger and binds each delivered model to an on-chain cryptographic fingerprint. The receiving AI actor verifies model integrity and provenance by matching the computed hash against the blockchain record, enabling non-repudiation and back-tracing of who provided which model and when. The resulting audit trail strengthens trust in MQTT-based model distribution and supports provenance-driven explainability for connected-vehicle AI.


DOI
HAL
Type:
Conférence
City:
Nice
Date:
2026-06-09
Department:
Systèmes de Communication
Eurecom Ref:
8723
Copyright:
© 2026 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/8723