MLP and RNN Based Intrusion Detection System Using Machine Learning with Stochastic Optimization

Mithlesh Kumar, Gargishankar Verma

Abstract: With common innovations like Internet of Things, Cloud Computing and Social Networking, a lot of traffic from these networks are produced. Thus, there is a requirement for Intrusion Detection Systems that screens the traffic and breaks down them progressively. In this paper, NSL - KDD is utilized to assess the AI calculations for Intrusion Detection (ID). The dataset are taken from publicly available data of different types of attacks in the network. Consequently, lessening and choosing a specific arrangement of components work on the speed and precision. Along these lines, features are chosen by utilizing Feature scaling and other ML approaches. We have directed a thorough trial on Intrusion Detection System (IDS) that utilizations AI calculations, in particular, MLP and RNN. We have utilized the previous model RNN with the MLP combined with some Stochastic Optimization. The proposed system architecture performs well in the commodity hardware.

Keywords: Intrusion Detection, IDS, Network Infiltration. Multi Layer Perceptron, Recurrent Neural Network, Machine Learning

How to Cite?: Mithlesh Kumar, Gargishankar Verma, "MLP and RNN Based Intrusion Detection System Using Machine Learning with Stochastic Optimization", Volume 10 Issue 12, December 2021, International Journal of Science and Research (IJSR), Pages: 158-161, https://www.ijsr.net/getabstract.php?paperid=MR211201200907, DOI: https://dx.doi.org/10.21275/MR211201200907

Download Citation: APA | MLA | BibTeX | EndNote | RefMan