You are on page 1of 3

ABSTRACT

As the Internet services spread all over the world, many kinds and
a large number of security threats are increasing. For the increased usage of
the internet, the intrusion detection system plays main role. Intrusion is an
unauthorized access of the network resource. The intruders may be a person
or any software program. The role of the IDS is to analyze the network
traffic and gives alerts about the attacks. Data mining is the process of
extracting datas from database. The IDS checks any illegal activities, while
extracting the data from database. In this project, we proposed a new
intrusion detection system using the association rules. Moreover, a new
feature selection algorithm based on the Conditional Random Field (CRF)
is proposed to improve the detection accuracy. The experimental results of
the proposed model show that this system detects anomalies with low false
alarm rate and high detection rate when tested with KDD Cup 99 data set.

Keywords: Intrusion detection System, Data mining, Association rule


mining and CRF.

LIST OF FIGURES
FIGURE NO.

FIGURE NAME

PAGE NO

4.1

SYSTEM ARCHITECTURE

14

5.1
5.2
5.3
7.1

DFD DIAGRAMS
DFD LAYER 0
DFD LAYER 1
DFD LAYER 2
Support and Confidence for

17
17
18
31

selected features
7.2

Nodes and their attacks

32

LIST OF ABBREVIATION
ACRONYM

ABBREVIATION

CRF

Conditional Random Fields

GNP

Genetic Network Programming

GA

Genetic Algorithm

GP
IDS

Genetic Programming
Intrusion Detection System

KDD

Knowledge Discovery and DataMining

You might also like