Title: Detection of malicious network traffic using enhanced neural network algorithm in big data

Authors: B. Rajendran; Saravanan Venkataraman

Addresses: PW Data Solutions, 11B Norwood Road, Southall, UB2 4EA, UK ' Department of Computer Science, College of Computer and Information Sciences, Majmaah University, Kingdom of Saudi Arabia

Abstract: Nowadays, the computing technologies and systems create big challenges to generate the large amount of data with the very biggest growth of internet. However, on the other hand, it also provides the light to the area of data analytics and mining. These areas are not working on the big data of uncovering the patterns and laws beneath. Recently, the analytics of big data are applied to areas. These areas are e-commerce, healthcare and industry. Security analytics receive a great attention based on big data. These analytics are based on the big data. This paper presents the verbose sketch of techniques. These techniques presented about the uses of big data. These applications of big data are placed in network security analytics. A new neural network algorithm is proposed to analyse network traffic. The worst data being sent through the networks and anomalous activities being carried out are detected by using this approach. An experiment is carried out using KDD dataset and the performance of the proposed approach is compared with traditional learning approaches in terms of false positive ratio and detection ratio.

Keywords: big data; threats; network security; mapping; neurons; similarity metric; optimisation target function; KDD dataset; neural network; centroid classifier.

DOI: 10.1504/IJAIP.2021.116366

International Journal of Advanced Intelligence Paradigms, 2021 Vol.19 No.3/4, pp.370 - 379

Received: 03 Apr 2018
Accepted: 12 Jun 2018

Published online: 09 Jul 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article