Modified Ant Miner for Intrusion Detection

Author

Agravat, Deven ; Vaishnav, Urmi ; Swadas, P.B.

Author_Institution

Dept. of Inf. Technol., G H Patel Coll. of Eng. & Technol., Vallabh Vidyanagar, India

fYear

2010

fDate

9-11 Feb. 2010

Firstpage

228

Lastpage

232

Abstract

This paper proposes Modified Ant Miner algorithm for intrusion detection. Ant Miner and its descendant have produced good result on many classification problems. Data mining technique is still relatively unexplored area for intrusion detection. In this paper, modification has been suggested in basic ant miner algorithm to improve accuracy and training time of algorithm. The KDD Cup 99 intrusion data set is used to evaluate our proposed algorithm and the result obtained from this experiment is compared with that of Support Vector Machine. It has been found that our proposed algorithm is more effective in case of DOS, U2R, and R2L type of attacks.

Keywords

data mining; pattern classification; security of data; support vector machines; DOS; KDD Cup 99 intrusion data set; R2L; U2R; classification problems; data mining technique; intrusion detection; modified ant miner algorithm; support vector machine; Computer networks; Data mining; Educational institutions; IP networks; Information technology; Intrusion detection; Machine learning; Support vector machine classification; Support vector machines; Telecommunication traffic; Ant Miner; Intrusion Detection; Support Vector Machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Computing (ICMLC), 2010 Second International Conference on

Conference_Location

Bangalore

Print_ISBN

978-1-4244-6006-9

Electronic_ISBN

978-1-4244-6007-6

Type

conf

DOI

10.1109/ICMLC.2010.52

Filename

5460736