Ensuring robust cybersecurity in next-generation networks has become a critical challenge due to the increasing sophistication of cyber threats, particularly Distributed Denial-of-Service (DDoS) attacks. Traditional detection approaches often suffer from high computational costs, poor adaptability to evolving attack patterns, and limited interpretability. In this work, we propose an AI-driven meta-model, called Meta-Model Multilayer Extreme Learning Machines (MM-MELM), designed to enhance anomaly detection and classification in NGNs. The proposed framework integrates multiple Multilayer Extreme Learning Machine (MELM) models into a meta-learning structure, leveraging the diverse outputs of independently trained MELMs to improve robustness and generalization. The proposed methodology is evaluated across multiple DDoS attack scenarios, demonstrating its capability to generalize across diverse threat types. Performance analysis reveals that MM-MELM achieves state-of-the-art attack detection, consistently outperforming baseline models. Moreover, MM-MELM exhibits lower variability across all evaluation metrics, ensuring robust performance regardless of the attack complexity. The results highlight that MM-MELM provides a trade-off solution among balanced accuracy, precision, recall, and F 1 -score, making it a highly scalable and adaptive solution for real-time network security.
Calle-Cancho et al. (Sat,) studied this question.