Ghazy, R., Khedr, E., Dessouky, M., ElFishawy, N., Abd El-Samie, F. (2018). Anomaly Intrusion Detection Based on PCA. test, 27(2), 141-150. doi: 10.21608/mjeer.2018.63184
Rania A. Ghazy; El-Sayed M. Khedr; Moawad I. Dessouky; Nawal A. ElFishawy; Fathi E. Abd El-Samie. "Anomaly Intrusion Detection Based on PCA". test, 27, 2, 2018, 141-150. doi: 10.21608/mjeer.2018.63184
Ghazy, R., Khedr, E., Dessouky, M., ElFishawy, N., Abd El-Samie, F. (2018). 'Anomaly Intrusion Detection Based on PCA', test, 27(2), pp. 141-150. doi: 10.21608/mjeer.2018.63184
Ghazy, R., Khedr, E., Dessouky, M., ElFishawy, N., Abd El-Samie, F. Anomaly Intrusion Detection Based on PCA. test, 2018; 27(2): 141-150. doi: 10.21608/mjeer.2018.63184

Anomaly Intrusion Detection Based on PCA

Menoufia Journal of Electronic Engineering Research
Article 6, Volume 27, Issue 2, July 2018, Pages 141-150
Document Type: Original Article
DOI: 10.21608/mjeer.2018.63184
Authors
Rania A. Ghazy1; El-Sayed M. Khedr1; Moawad I. Dessouky1; Nawal A. ElFishawy2; Fathi E. Abd El-Samie1
1Dept. of Electronics and Electrical Communications, Faculty of Electronic Engineering, Minufiya University.
2Department of Computer Science and Engineering, Faculty of Electronic Engineering, Menoufia
Abstract
This paper proposes an anomaly intrusion detection approach
based on the Principal Component Analysis (PCA) model and
selecting different numbers of effective features, from the
dataset in the presence of several types of attacks. Several
attacks have been considered such as Denial of Service (DoS),
Probing (Prob), Remote to Local (R2L), and User to Root
(U2R) attack. Simulation results conclude that more accuracy
of detection and less false alarms are obtained, in spite of
reducing the number of selected features, and subsequently
reducing complexity.
References
[1] S. Kent “On the trial of intrusions into information systems”, IEEE Spectrum, pp.52-56. Dec. 2000. [2] Chakraborty, B. Feature Subset Selection by Neuro-Rough Hybridization. Lecture Notes in Computer Science (LNCS), Springer, Heidelberg, 2005 [3] Sung, A. H. and Mukkamala, S. Identifying Important Features for Intrusion Detection Using Support Vector Machines and Neural Networks, Proceedings of International Symposium on Applications and the Internet (SAINT) pp. 209-216, 2003

[4] M. Elrawy, M. F.Abdelhamid and T. K., A. M. “ IDS in
Telecommunication Network Using PCA”, (IJCNC), Vol.5, No.4, pp. 147- 157, Jul. 2013. [5] Gh.R .Zargar and T. Baghaie “Category-Based intrusion detection
using PCA”, Journal of Information Security, 3, pp. 259-271,2012. [6] https://en.wikipedia.org/wiki/Principal_component_analysis, (Access date 2017). [7] I. Jolliffe,“Principal Component Analysis”, 2nd Springer Verlag, 2002. [8] L. Shyu, S. Sarinnapakorn,K. Chang, andM. Chen,“A novel anomaly
detection scheme based on principal component classifier”, IEEE foundation(ICDM03), pp. 172-179, 2003. [9] http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html (Access date 2017). [10]S.K. Sahu, S. Sarangi and S.K. Jena “A Detail Analysis on Intrusion
Detection Datasets”, IEEE International Advance Computing Conference (IACC), 2014.

Statistics
Article View: 151