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

Cybersecurity threats have become increasingly complex due to the rapid growth of cloud computing, Internet of Things (IoT), mobile networks, and remote digital infrastructures. Traditional intrusion detection and response systems are often limited by static rules, high false alarm rates, and inability to adapt to emerging attack patterns. This research proposes an AI-driven cyberthreat detection and automated response model based on a hybrid optimization strategy called the Firefly  and Whale Optimization (F&WO) algorithm. The F&WO algorithm integrates structured exploration inspired by forest growth mechanisms with exploitation strategies inspired by Grey Wolf Optimization (GWO). This hybrid design supports efficient feature selection, hyperparameter tuning, and response prioritization to improve both detection accuracy and response speed. The proposed framework is evaluated using standard cybersecurity datasets including NSL-KDD, UNSW-NB15, and CICIDS2017. Experimental results show that the F&WO-assisted model achieves high classification accuracy, strong precision and recall, reduced false positive rates, and faster decision-making for response automation compared to non-optimized and single-heuristic models. The findings indicate that the proposed approach offers a reliable and scalable solution for intelligent cyber defense systems capable of operating in dynamic real-world network environments.