The dramatically development of internet,
Security of network traffic is becoming a major issue of
computer network system. Attacks on the network are
increasing day-by-day. The Hybrid framework would
henceforth, will lead to effective, adaptive and intelligent
intrusion detection. In this paper, We propose a hybrid
fuzzy rough with Naive bayes classifier, Support Vector
Machine and K-nearest neighbor (K-NN) based classifier
(FRNN) to classify the patterns in the reduced datasets,
obtained from the fuzzy rough bioinspired algorithm search.
The proposed hybrid is subsequently validated using real-life
datasets obtained from the University of California, Irvine
machine learning repository. Simulation results demonstrate
that the proposed hybrid produces good classification
accuracy. Finally, parametric and nonparametric statistical
tests of significance are carried out to observe consistency of
the classifiers.
Namita Parati : is working as Assistant
Professor at Bhoj Reddy Engineering
College for Women, Hyderabad,
INDIA. She has received B.E,
M.Tech Degree in Computer Science
and Engineering. Her main research
interest includes intrusion detection
using hybrid network.
Sumaltha Potteti : is working as
Assistant Professor at Bhoj
Reddy Engineering College for
Women, Hyderabad, INDIA.
She has received B.Tech,
M.Tech Degree in Computer
Science and Engineering. Her
main research interest includes
Cloud computing and intrusion
detection
Intrusion Detection System (IDS)
Data Mining
Classification
Support vector machines (SVM)
K-Nearest Neighbor (KNN)
Naive Bayes Classifier
This paper proposes an envisioning framework for
intrusion detection i.e. Hybrid Intrusion Detection System.
The developed framework is an intelligent, adaptive and
effective intrusion detection framework. The experimental
analysis is performed on the developed IDS framework
and is compared with other techniques present in the
scenario. The resultants obtained convey that the
developed hybrid framework is highly effective to
overcome the deficiencies found in previous work. As the
framework uses two data mining techniques (i.e. TAN and
SVM) to breed the classification rules, it can be
effortlessly implemented in real time and is able to detect
and adapt new types of intrusive activities. Also
experimental assessment shows that the developed
framework has reduced the false alarm rate and increased
the accuracy up to noteworthy extend which is a major
concern in case of intrusion detection mechanism. In
addition to this, the framework is able to detect U2R and
R2L attacks more efficiently than previous findings,
boosting up the detection process. In future, some more
work can be made in order to detect U2R and R2L attacks
more accurately which may tend to further enhance the
system efficiency.
[1] KDDCUP-99 task description.
https://kdd.ics.uci.edu/databases/kddcup99/task.html.
[2] Deepthy K Denatious & Anita John, “Survey on Data
Mining Techniques to Enhance Intrusion Detection”,
International Conference on Computer Communication
and Informatics (ICCCI -2012), Jan. 10 – 12, 2012,
Coimbatore, INDIA
[3] Srinivas Mukkamala, Andrew H. Sung, Ajith Abraham,
Intrusion detection using an ensemble of intelligent
paradigms, Elsevier, Journal of Network and Computer
Applications 28 (2005) pp.-167–182.
[4] Sandhya Peddabachigari, Ajith Abraham,Crina Grosan,
Johnson Thomas, Modeling intrusion detection system
using hybrid intelligent systems, Elsevier, Journal of
Network and Computer Applications 30 (2007), pp.114-
132.
[5] KddCup99 dataset, available at
http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html,
1999.
[6] Rung-Ching Chen, Kai-Fan Cheng and Chia-Fen Hsieh,
“Using Rough Set And Support Vector Machine For
Network Intrusion Detection”, International Journal of
Network Security & Its Applications (IJNSA), Vol 1, No
1, April 2009
[7] Kohavi R, John GH (1997) Wrappers for feature subset
selection. Artif Intell 97:273–324
[8] Wei-Hao Lin and Alexander Hauptmann, Metaclassification:
Combining Multimodal Classifiers,
Springer, Mining Multimedia and Complex Data, LNAI
2797 (2003) pp. 217–231.
[9] Peddabachigiri S., A. Abraham., C. Grosan and J.
Thomas, “Modeling of Intrusion Detection System Using
Hybrid intelligent systems” , Journals of network
computer application, 2007
[10] Mrutyunjaya Panda and Manas Ranjan Patra, “A
Comparative Study Of Data Mining Algorithms For
Network Intrusion Detection”, First International
Conference on Emerging Trends in Engineering and
Technology, pp 504-507, IEEE, 2008
[11] M.Govindarajan and Rlvl.Chandrasekaran, “Intrusion
Detection Using k-Nearest Neighbor” pp 13-20, ICAC,
IEEE, 2009
[12] Mohammadreza Ektefa, Sara Memar, Fatimah Sidi and
Lilly Suriani Affendey, “Intrusion Detection Using Data
Mining Techniques”, pp 200-203, IEEE, 2010FRNN(U,
C, y)
[13] Roshan Chitrakar and Huang Chuanhe, “Anomaly based
Intrusion Detection using Hybrid Learning Approach of
combining k-Medoids Clustering and Naïve Bayes
Classification”, IEEE,2012
[14] David Ndumiyana, Richard Gotora and Hilton
Chikwiriro, “Data Mining Techniques in Intrusion
Detection: Tightening Network Security”, International
Journal of Engineering Research & Technology (IJERT),
Vol. 2 Issue 5, May – 2013
[15] Muhammad K. Asif, Talha A. Khan,Talha A. Taj, Umar
Naeem and Sufyan Yakoob, “ Network Intrusion
Detection and its Strategic Importance”, Business
Engineering and Industrial Applications
Colloquium(BEIAC), IEEE, 2013
[16] Kapil Wankhade, Sadia Patka and Ravindra Thools, “An
Efficient Approach for Intrusion Detection Using Data
Mining Methods”, IEEE 2013
[17] Vaishali B Kosamkar and Sangita S Chaudhari, “Data
Mining Algorithms for Intrusion Detection System: An
Overview”, International Conference in Recent Trends in
Information Technology and Computer Science
(ICRTITCS), 2012
[18] Iwan Syarif, Adam Pruge Bennett and Gary Wills,
“Unsupervised clustering approach for network anomaly
detection”, IEEE.
[19] Wei-Hao Lin and Alexander Hauptmann, Metaclassification:
Combining Multimodal Classifiers,
Springer, Mining Multimedia and Complex Data, LNAI
2797 (2003) pp. 217–231. [20] Alexandra M. Carvalho, Arlindo L. Oliveira and Marie-
France Sagot, Efficient learning of Bayesian network
classifiers: An extension to the TAN classifier,
Proceedings of Advances in Artificial Intelligence,
Springer, Volume 4830, (2007), pp 16-25.
[21] Ajit Singh, Tree-augmented naive bayes, Homework 2
Problem 7 of Probabilistic Graphical Models, Fall 2006.