Aquila Optimization Algorithm based Feature Selection with Optimal Machine Learning for Security Internet of Things Environment

Internet of Things (IoT) supported Distributed Denial of Service (DDoS) attack recognition is a dangerous part of cyber-security that mainly concentrates on classifying and modifying malicious actions directing IoT devices and networks. These attacks contain a multitude of cooperated IoT devices, synchronized to beat an objective with an extreme volume of traffic, executing it unreachable. Detection devices frequently use machine learning (ML), anomaly recognition, and traffic analysis which play an essential part in identifying these attacks as well as executing countermeasures to defend IoT organizations. IoT DDoS attack recognition aids guarantee availability and reliability of IoT services and devices, safeguarding a massive and consistent landscape of smart devices that support our current digital world. In this feature, this study develops an Aquila Optimization Algorithm based Feature Selection with Optimal ML (AOAFS-OML) method for DDoS attack detection in an IoT environment. The presented technique includes a multi-faceted technology, starting with feature selection via Aquila optimizer (AO), aimed at enhancing significance of input data for better precision. For robust detection, this model uses dominant XGBoost model which is familiar for its competence in handling difficult datasets. To improve performance, parameter tuning is attained by employing an advanced Artificial Rabbit Optimization (ARO) model. An AOAFS-OML method signifies an important development in IoT DDoS attack recognition, providing an accurate and effectual solution to identify and mitigate malicious actions within IoT systems. By improving exactness, rapidity as well as flexibility, it authorizes cybersecurity experts to defend IoT organizations and safeguard flexibility and safety of consistent devices and services that are essential to our current digital network.