An Adaptive F&WO Algorithm-Driven Model for Next-Generation Cyberthreat Detection and Response

The rapid expansion of cloud computing, Internet of Things (IoT), mobile platforms, and distributed digital infrastructures has significantly increased the complexity and scale of cybersecurity threats. Traditional intrusion detection systems (IDS) rely heavily on predefined rules and signatures, which often fail to detect evolving and sophisticated attacks. Additionally, many conventional detection systems suffer from high false positive rates and limited adaptability to dynamic network environments. This research proposes an intelligent cyberthreat detection and response framework using a hybrid Firefly and Whale Optimization (F&WO) algorithm integrated with machine learning. The model performs feature selection, hyperparameter tuning, and automated response prioritization to improve the efficiency of intrusion detection. By combining the exploration ability of the Firefly algorithm with the exploitation capability of Whale Optimization techniques, the proposed approach achieves improved optimization performance.

The framework is evaluated using widely used cybersecurity datasets including NSL-KDD, UNSW-NB15, and CICIDS2017. Experimental results demonstrate that the proposed F&WO-optimized model improves classification accuracy, precision, recall, and response efficiency while reducing false alarm rates compared with conventional approaches. The study highlights the potential of hybrid metaheuristic optimization techniques for building adaptive and intelligent cybersecurity defense systems capable of handling modern network threats.