Enhanced Crow Search with Deep Learning-Based Cyberattack Detection in SDN-IoT Environment

The paradigm shift towards the Internet of Things (IoT) phenomenon and rise edge-computing models provide massive potential for several upcoming IoT applications like smart grid, energy, home, health transportation services. However, it also provides a sequence novel cyber-security issues. Although networks advantages, heterogeneous nature network wide connectivity devices make easy cyber-attackers. Cyberattacks result in financial loss data breaches organizations individuals. So, becomes crucial to secure environment from such cyberattacks. With this motivation, current study introduces an effectual Enhanced Crow Search Algorithm with Deep Learning-Driven Cyberattack Detection (ECSADL-CAD) model Software-Defined Networking (SDN)-enabled environment. presented ECSADL-CAD approach aims identify classify cyberattacks SDN-enabled To attain this, initially pre-processes data. In model, Reinforced Belief Network (RDBN) is employed attack detection. At last, ECSA-based hyperparameter tuning process gets executed boost overall classification outcomes. A series simulations were conducted validate improved outcomes proposed model. experimental confirmed superiority over other existing methodologies.