Adapting deep learning-LSTM method using optimized dataset in SDN controller for secure IoT

The Internet of Things (IoT) has grown into various enterprises. While the IoT ecosystem's extensive and open environment has many advantages, it can also be a target for a range of growing cyber risks and assaults. The benefits of device integration into a smart ecosystem are enhanced by the IoT's diversity, but the IoT's diverse nature makes establishing a single security solution difficult. However, software-defined network’s (SDNs) centralized intelligence and programmability, it is now possible to put together a single, effective security solution to combat cyber threats and attacks. This study proposes a DL-driven SDN-enabled IoT framework that practices a Deep Neural Network-Long Short-Term Memory classifier to quickly and efficiently detect sophisticated multisector malware botnets. The proposed mechanism was rigorously tested utilizing the most recent state-of-the-art dataset, CICIDS2017, as well as traditional performance evaluation metrics. Furthermore, the proposed technique is compared to current industry norms (i.e., DL algorithms). Extensive testing shows that the proposed method surpasses the competition in terms of detection accuracy while requiring just a minimal compromise in terms of computational cost.