Deep learning model for intrusion detection system utilizing convolution neural network

Abstract An integral part of any reliable network security infrastructure is the intrusion detection system (IDS). Early attack can stop adversaries from further intruding on a network. Machine learning (ML) and deep (DL) techniques to automate threat at scale never previously envisioned have snowballed during past 10 years. Researchers, software engineers, professionals been encouraged reconsider use ML techniques, notably in cybersecurity. This article proposes for detecting with two approaches, first utilizing proposed hybrid convolutional neural (CNN) Dense layers. The second utilizes naïve Bayes (NB) compares approaches determine best accuracy. preprocessing data necessary. suggested technique evaluated using UNSW-NB15 Dataset create classifier an effective IDS. experimental results CNN-dense outperformed DL models. CNN has 99.8% accuracy rate compared previous studies. At same time, Gaussian Bayes, which considered among ML-utilized classifiers, yielded 83% rate.