Skip to main content

Big data security analysis approach using Computational Intelligence techniques in R for desktop users.

Naik, N., Jenkins, P., Savage, N. and Katos, V., 2017. Big data security analysis approach using Computational Intelligence techniques in R for desktop users. In: IEEE Symposium Series on Computational Intelligence (SSCI), 6-9 Dec 2016, Athens, Greece.

Full text available as:

[img]
Preview
PDF
07849907.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

1MB

DOI: 10.1109/SSCI.2016.7849907

Abstract

© 2016 IEEE.Big Data security analysis is commonly used for the analysis of large volume security data from an organisational perspective, requiring powerful IT infrastructure and expensive data analysis tools. Therefore, it can be considered to be inaccessible to the vast majority of desktop users and is difficult to apply to their rapidly growing data sets for security analysis. A number of commercial companies offer a desktop-oriented big data security analysis solution; however, most of them are prohibitive to ordinary desktop users with respect to cost and IT processing power. This paper presents an intuitive and inexpensive big data security analysis approach using Computational Intelligence (CI) techniques for Windows desktop users, where the combination of Windows batch programming, EmEditor and R are used for the security analysis. The simulation is performed on a real dataset with more than 10 million observations, which are collected from Windows Firewall logs to demonstrate how a desktop user can gain insight into their abundant and untouched data and extract useful information to prevent their system from current and future security threats. This CI-based big data security analysis approach can also be extended to other types of security logs such as event logs, application logs and web logs.

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Science & Technology
ID Code:28945
Deposited By: Symplectic RT2
Deposited On:19 Apr 2017 15:48
Last Modified:14 Mar 2022 14:04

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -