A convolutional neural network-based intrusion detection system that was evaluated using the CIC-IDS2017 dataset and aims to deliver a low false alarm rate, high accuracy, and a high detection rate.
The field of information technology is undergoing a global revolution; information is exchanged globally. Such action requires the existence of an effective data and network protection system. IDS can provide security, protect the network from attacks and threats, and identify potential security breaches. In this paper, we developed a convolutional neural network-based intrusion detection system that was evaluated using the CIC-IDS2017 dataset. For newly public datasets, our model aims to deliver a low false alarm rate, high accuracy, and a high detection rate. The model achieved a 99.55 percent detection rate and 0.12 FAR using CIC-IDS2017 multiclass classification.