Biomedical Engineering Reference
In-Depth Information
Introduction
Intrusion Detection Systems are one of the important building blocks of a secure,
reliable network, and are used widely along with other security programs and
concepts. There are several methods used to implement intrusion detection such as
statistical analysis expert systems, state transition approaches, etc., and these
several approaches are based on the immune system that were proposed in the
recent years. The goal of Intrusion Detection is to detect illicit access and abuse of
computer systems by both system insiders and external intruders, and guarantee
the system integrity, confidentiality, and usability. Several techniques are used to
achieve intrusion detection such as expert systems, state transition approaches, and
statistical analysis. However, they are inefficient to detect the unknown intrusions.
Therefore, several approaches based on the immune system were proposed in the
recent years [
1
].
Artificial immune system for detecting intrusion has become a new approach in
security research. Artificial immunology is an interdisciplinary between biology
and information security. AIS is inspired from the human immune system (HIS)
which is a system of structures in the human body that recognizes the foreign
pathogens and cells from human body cells and protects the body against those
disease [
2
].
In this paper we compare two popular algorithms that represent two different
intrusion detection techniques. One is dendritic cell algorithm based on belief
theory (DCA-BE) and the other is the DCA classification algorithm. The experi-
ment's data come from the KDD CUP competition data set. These data are part of
the data collected from the MIT Lincoln Labs 1998 DARPA Intrusion Detection
Evaluation Program and are considered as benchmark data for evaluating the
intrusion detection system [
3
]. The performance of an intrusion detection system
may be evaluated in terms of TP rate and FP rate.
The rest of the paper is organized as follows. Section two deals with the
Related
Work
. Section three briefly describes two algorithms,
Dendritic Cell Algorithm
Based on Dempster Belief Theory
and
Dendritic Cell Algorithm
. Section four is
about
Experiment Result Discussion
and finally section five is the
Conclusion
of
this experiment.
Related Work
In recent years, use of Artificial Immune System (AIS) has been favored by the
researcher to build Intrusion Detection Systems based on it. AIS is a new branch of
computational intelligence. The primitive theoretical study on artificial immu-
nology was conducted by Farmer in 1986 [
4
]. They put forward a new link
between biological and computing science [
1
]. Forrest et al. in 1994, proposed the
most effective idea in utilization of immunity in computer security for self and
Search WWH ::
Custom Search