CNN-IDS: Convolutional Neural Network for Network Intrusion Detection System

Asmaa Halbouni, Teddy Surya Gunawan, Murad Halbouni, Faisal Ahmed Assaig, Mufid Ridlo Effendi, Nanang Ismail

202230 citationsDOI

Abstract

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.

Topics & Concepts

Computer scienceConvolutional neural networkIntrusion detection systemConstant false alarm rateField (mathematics)Network securityData miningArtificial intelligenceArtificial neural networkComputer securityMachine learningMathematicsPure mathematicsNetwork Security and Intrusion DetectionAdvanced Malware Detection TechniquesAnomaly Detection Techniques and Applications