A Privacy-Preserving Digital Twin Framework for the Metaverse Based on Zero-Knowledge Proofs and Federated Learning

Abstract

Privacy of users and security of data are important issues that will be exposed to use in the Metaverse by use of Digital Twins (DTs). The current paper suggests a privacy-preserving system, which combines Zero-Knowledge Proofs (ZKPs) of secure identity verification and Federated Learning (FL) of decentralized model training. The framework allows for alleviating the risk of storing data in central facilities and preventing unauthorized access by locally processing data and using cryptographic solutions. The results produced by the evaluation prove that the proposed system is capable of attaining the necessary level of privacy of its users and ensuring reliable and scalable communications within the Metaverse applications.