Intrusion Detection System for Wireless Networks

Rashid Baimukashev, Kamalkhan Artykbayev, Adam Kazybek, Mels Begenov

2021

Full text Open access: Green Metadata (CSL-JSON)

DOI 10.1109/icecco53203.2021.9663787

Data confidence 70 medium

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The network security plays a vital role in the performance of the wireless networks, and as a part of network security features the intrusion detection system may enhance the performance of the network. In our project we designed such intrusion detection system using deep learning approaches such as CNN, RNN and LSTM as well as with traditional machine learning algorithms such as SVM, Random Forest and XGBoost. In our project we achieved a near to state-of-the-art performance on detecting network attacks on the NSL-KDD dataset.