Modified Of Evaluating Shallow And Deep Neural Networks For Network Intrusion Detection Systems In Cyber Security

Abstract

Abstract—Intrusion Detection Systems (IDS) have developed into a crucial layer in all contemporary Information and Communication Technology (ICT) systems as a result of a demand for cyber safety in real-world situations. IDS advises integrating Deep Neural Networks (DNN) because, among other things, it might be challenging to identify certain types of assaults and advanced cyberattacks are complex (DNNs). DNNs were employed in this study to anticipate Network Intrusion Detection System attacks (N-IDS). The network has been trained and benchmarked using the KDDCup-'99 dataset, and a DNN with a learning rate of 0.001 is used, running for 10 epochs for using the activation model experiment and 8 epochs for using the TensorFlow experiment. Keywords—Intrusion detection system, deep neural networks, machine learning, deep learning