In this work, a novel framework for detecting mali-cious networks in the IoT-enabled Metaverse networks to ensure that malicious network traffic is identified and integrated to suit optimal Metaverse cybersecurity is presented. First, the study raises a core security issue related to the cyberthreats in Metaverse networks and its privacy breaching risks. Second, to address the shortcomings of efficient and effective network intrusion detection (NIDS) of dark web traffic, this study employs a quantization-aware trained (QAT) 1D CNN followed by fully con-nected networks (ID CNNs-GRU-FCN) model, which addresses the issues of and memory contingencies in Metaverse NIDS models. The QAT model is made interpretable using eXplainable artificial intelligence (XAI) methods namely, SHapley additive exPlanations (SHAP) and local interpretable model-agnostic ex-planations (LIME), to provide trustworthy model transparency and interpretability. Overall, the proposed method contributes to storage benefits four times higher than the original model without quantization while attaining a high accuracy of 99.82 \%.