LSTM-GRU Based Efficient Intrusion Detection in 6G-Enabled Metaverse Environments

In response to the growing security demands of the 6G-enabled Metaverse, this paper introduces an efficient intrusion detection system utilizing a novel LSTM-GRU-based neural network. The model capitalizes on the sequential data processing prowess of LSTM and GRU layers to discern complex patterns indicative of cyber threats. Evaluated on a diverse dataset, the model architecture demonstrated significant accuracy improvements over traditional machine learning methods, achieving a 0.90 overall accuracy with high precision across various attack classes. Our results, presented through loss and accuracy trends, confusion matrices, and classification reports, attest to the model's robustness and generalizability. This study proposes a promising approach to safeguarding the Metaverse-6G convergence, marking a step forward in predictive cybersecurity measures.