Urban Metaverse Cyberspaces & Blockchain-Enabled Privacy-Preserving Machine Learning Authentication With Immersive Devices

Abstract

Ensuring secure and reliable urban metaverse cyberspaces requires addressing two critical challenges, namely, cybersecurity and privacy protection. In the upcoming years, it is anticipated that cybercrime activities will be widespread in this ecosystem, which has trillions of dollars in economic value. This report explores a Blockchain-Facilitated Federated Security-Preserving Deep Learning (BF-FSPDL) authentication and verification method using immersive metaverse devices. Blockchain technology and Federated Learning (FL) are merged not only to eliminate the requirement of a trusted third party for the verification of the authenticity of transactions and immersive actions, but also, to avoid Single Point of Failure (SPoF) and Generative Adversarial Networks (GAN) attacks by detecting the malicious nodes using the majority voting mechanism. The developed approaches in this research have been tested using Motion Capture Suits (MoCaps) in a co-simulation environment with the Proof of Work (PoW) consensus mechanism. The preliminary results prove the viability of employing the proposed approaches in realising the objectives presented in this report. The results suggest that the approaches can prevent impersonation, identity theft, and theft of credentials or avatars promptly before any transactions have been executed. The proposed system will be tested with a larger number of nodes involving the Proof of Stake (PoS) consensus mechanism using several other metaverse immersive devices as future work.