Abstract
One of the key elements in any computers network security protocol is an intrusion detection system (IDS). With the recent advances and growth of various wireless technologies, it is imperative to implement robust IDSs in so as to detect malicious activities accurately. This paper proposes the implementation of a Deep Gated Recurrent Unit (DGRU) Based classifier as well as a wrapper-based feature extraction algorithm forWireless IDS.We assess the performance of the DRGU IDS models with the help of the NSL-KDD benchmark dataset. Furthermore, we compare our framework to popular algorithms including Artificial Neural Networks, Deep Long-Short Term Memory (DLSTM), Random Forest, Naive Bayes and Feed Foward Deep Neural Networks. The experiments outcome demonstrates that the DGRU IDS displays a significant increase in performance over existing methods.