Enhanced Cyber Threat Detection Using Hybrid Firefly, Whale, and Grey Wolf Optimization Algorithms

Cybersecurity threats have become increasingly sophisticated due to the rapid growth of digital infrastructures, cloud computing, Internet of Things (IoT), and artificial intelligence-driven attacks. Traditional intrusion detection systems often suffer from high false-positive rates, slow convergence, and limited adaptability to dynamic attack patterns. Metaheuristic optimization algorithms have emerged as promising approaches for improving cyber threat detection by enhancing feature selection, classification accuracy, and optimization efficiency. This paper proposes a comparative framework based on a Hybrid Firefly–Whale–Grey Wolf Optimization (FWGWO) algorithm for cyber threat detection. The proposed hybrid model integrates the exploration capability of Firefly Optimization (FA), the exploitation strength of Whale Optimization Algorithm (WOA), and the leadership-based hunting mechanism of Grey Wolf Optimization (GWO). The framework is evaluated using benchmark cybersecurity datasets such as NSL-KDD, CICIDS2017, and UNSW-NB15. Experimental results demonstrate that the hybrid FWGWO approach improves detection accuracy, convergence speed, precision, recall, and F1-score while reducing computational complexity and false alarms compared to standalone optimization methods. The proposed framework provides an efficient and adaptive solution for intelligent cyber threat detection in modern network environments.