An Ensemble Approach for Cyber Attack Detection System: A Generic Framework
Cyber attack detection is based on assumption that intrusive activities are noticeably different from normal system activities and thus detectable. A cyber attack would cause loss of integrity, confidentiality, denial of resources. The fact is that no single classifier is able to give maximum accura...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2014-04-01
|
Series: | International Journal of Networked and Distributed Computing (IJNDC) |
Subjects: | |
Online Access: | https://www.atlantis-press.com/article/11820.pdf |
_version_ | 1811173610412310528 |
---|---|
author | Shailendra Singh Sanjay Silakari |
author_facet | Shailendra Singh Sanjay Silakari |
author_sort | Shailendra Singh |
collection | DOAJ |
description | Cyber attack detection is based on assumption that intrusive activities are noticeably different from normal system activities and thus detectable. A cyber attack would cause loss of integrity, confidentiality, denial of resources. The fact is that no single classifier is able to give maximum accuracy for all the five classes (Normal, Probe, DOS, U2R and R2L). We have proposed a Cyber Attack Detection System (CADS) and its generic framework, which performs well for all the classes. This is based on Generalized Discriminant Analysis (GDA) algorithm for feature reduction of the cyber attack dataset and an ensemble approach of classifiers for classification of cyber attacks. The ensemble approach of classifiers classifies cyber attack based on the union of the subsets of features. Thus, it can detect a wider range of attacks. The C4.5 and improved Support Vector Machine (iSVM) classifiers are combined as a hierarchical hybrid classifier (C4.5-iSVM) and an ensemble approach combining the individual base classifiers and hybrid classifier for best classification of cyber attacks. The experimental results illustrate that the proposed Cyber Attack Detection System is having higher detection accuracy for the all classes of attacks with minimize training, testing times and false positive alarm. |
first_indexed | 2024-04-10T17:49:48Z |
format | Article |
id | doaj.art-7d299558b0564921aa4aba3d1ba5b3a0 |
institution | Directory Open Access Journal |
issn | 2211-7946 |
language | English |
last_indexed | 2024-04-10T17:49:48Z |
publishDate | 2014-04-01 |
publisher | Springer |
record_format | Article |
series | International Journal of Networked and Distributed Computing (IJNDC) |
spelling | doaj.art-7d299558b0564921aa4aba3d1ba5b3a02023-02-02T22:19:44ZengSpringerInternational Journal of Networked and Distributed Computing (IJNDC)2211-79462014-04-012210.2991/ijndc.2014.2.2.2An Ensemble Approach for Cyber Attack Detection System: A Generic FrameworkShailendra SinghSanjay SilakariCyber attack detection is based on assumption that intrusive activities are noticeably different from normal system activities and thus detectable. A cyber attack would cause loss of integrity, confidentiality, denial of resources. The fact is that no single classifier is able to give maximum accuracy for all the five classes (Normal, Probe, DOS, U2R and R2L). We have proposed a Cyber Attack Detection System (CADS) and its generic framework, which performs well for all the classes. This is based on Generalized Discriminant Analysis (GDA) algorithm for feature reduction of the cyber attack dataset and an ensemble approach of classifiers for classification of cyber attacks. The ensemble approach of classifiers classifies cyber attack based on the union of the subsets of features. Thus, it can detect a wider range of attacks. The C4.5 and improved Support Vector Machine (iSVM) classifiers are combined as a hierarchical hybrid classifier (C4.5-iSVM) and an ensemble approach combining the individual base classifiers and hybrid classifier for best classification of cyber attacks. The experimental results illustrate that the proposed Cyber Attack Detection System is having higher detection accuracy for the all classes of attacks with minimize training, testing times and false positive alarm.https://www.atlantis-press.com/article/11820.pdfGeneralized Discriminant Analysis improved Support Vector MachineC4.5Cyber Attack Detection SystemHybrid systemEnsemble approach |
spellingShingle | Shailendra Singh Sanjay Silakari An Ensemble Approach for Cyber Attack Detection System: A Generic Framework International Journal of Networked and Distributed Computing (IJNDC) Generalized Discriminant Analysis improved Support Vector Machine C4.5 Cyber Attack Detection System Hybrid system Ensemble approach |
title | An Ensemble Approach for Cyber Attack Detection System: A Generic Framework |
title_full | An Ensemble Approach for Cyber Attack Detection System: A Generic Framework |
title_fullStr | An Ensemble Approach for Cyber Attack Detection System: A Generic Framework |
title_full_unstemmed | An Ensemble Approach for Cyber Attack Detection System: A Generic Framework |
title_short | An Ensemble Approach for Cyber Attack Detection System: A Generic Framework |
title_sort | ensemble approach for cyber attack detection system a generic framework |
topic | Generalized Discriminant Analysis improved Support Vector Machine C4.5 Cyber Attack Detection System Hybrid system Ensemble approach |
url | https://www.atlantis-press.com/article/11820.pdf |
work_keys_str_mv | AT shailendrasingh anensembleapproachforcyberattackdetectionsystemagenericframework AT sanjaysilakari anensembleapproachforcyberattackdetectionsystemagenericframework AT shailendrasingh ensembleapproachforcyberattackdetectionsystemagenericframework AT sanjaysilakari ensembleapproachforcyberattackdetectionsystemagenericframework |