CONFIDENTIAL6G

This use case focuses on the validation of functionalities for (i) Verifiable credentials and anonymous credentials with decentralised identities for achieving software updates; (ii) federated learning for model uploading and downloading car data with models deployed on a blockchain (CAN adapter connected to a car with memory to evaluate the processes); (iii) evaluation of secured and privacy-preserving communication and aggregation of the models in the FL server, and how to protect these from FL attacks such as membership inference, attribute inference, data reconstruction attacks, or data poisoning attacks, and potentially side-channel attacks. This use case will set up and operate a cloud and edge computing testbed. The goal is to assess the results and data produced from connected vehicles to drive emulations of FL model building when 5G or 6G infrastructure is being used in order to optimise network connectivity using 5/6G antenna technology and hierarchical and scalable edge computing infrastructure.