Securing IoT-enabled Metaverse with Authentication and Threat Classification Framework Using DL

In the current technological landscape, the rise of Web 3.0 is notable. Alongside this, immersive technologies like Virtual Reality (VR) and Augmented Reality (AR) are gaining increased popularity. This is due to idea like the Metaverse, which is a spatial computing platform that offers virtual experiences replicating real environments. However, Metaverse also faces security vulnerabilities, such as the risk of identity theft, financial fraud, and the damage of virtual assets due to the public openness of the platform. To mitigate these paramount concerns, there has to be a robust user authentication and verification approach before granting access to these domains. We propose a Convolutional Neural Networks (CNN)-based approach, i.e., MetaSec, which focuses on analyzing incoming user traffic patterns to identify any anomaly in the Internet of Things (IoT)-enabled Metaverse environment. The performance evaluation of MetaSec has been done using various optimization algorithms such as Stochastic Gradient Descent (SGD), Adam, RMSprop, and Adagrad. The main goal of rigorous assessment is to identify the most effective optimization approach for enhancing virtual network security. Thus, MetaSec proactively uncovers potential susceptibility and minimises the risk of intrusion and harm to critical resources. These hardware and software plug-in ranges from computer systems, networks, databases, websites, and other network-based applications and services applied in the virtual domain.