IJSRSET151370 | Received: 15 June 2015 | Accepted: 21 June 2015 | May-June 2015 [(1)3: 309-315]
© 2015 IJSRSET | Volume 1 | Issue 3 | Print ISSN : 2395-1990 | Online ISSN : 2394-4099
Themed Section: Engineering and Technology
309
Efficient calculation of fitness function by calculating reward
Penalty for a GA-based Network Intrusion Detection System
Prof. Jahnavi. S. Vithalpura, Prof. H. M. Diwanji
Department of Computer-IT, L. D. College of engineering, Ahmadabad, Gujarat, India
ABSTRACT
Our network is facing a rapidly evolving threat landscape full of modern applications, exploits, malware and
attack strategies that are capable of avoiding traditional methods of detection. Intrusion detection can perform the
task of monitoring usability systems to detect any apparition of insecure states. To overcome above mentioned
issues we have employed genetic algorithm to improve detection rate of intrusion detection system. To generate
healthy rule pool we have focused in design of fitness function. We have proposed a new fitness function based
on reward & penalty. This function make chromosome stronger by applying reward and remove weakness from it
by deducting penalty. So such a healthy chromosomes generates a best fit population which is reducing false
alarm rate and increasing a detection rate. In our work, we have classified a dataset as a normal record or attack
record using seven network features and calculated detection rate and false alarm rate. Further we have classified
DOS, Probe, and U2R and R2L type of attack from attack cluster. We measured improved efficiency of proposed
system by observing improvement in detection rate and reduction in false alarm rate.
Keywords: Genetic Algorithm, Intrusion, Network Intrusion Detection System, Fitness Function, Reward
Penalty.
I. INTRODUCTION
Intrusion detection system is a process of monitoring
network activities [1], presented and available in
computer network and investigate it’s for detection of
violating threats which could affect computer security
strategies and security practices. Now-a-day our network
system should play an important role in society to
prevent computers from malicious threats. At a situation
of transferring files and communication to be held on the
network we should probably focusing network security.
Intruders are more available in network to capture
important files and materials and do some malicious
activities in the computer system. Attacks are
categorized into [2], four types. There are DOS, U2R,
R2L and Probe. These attacks are classified by some
optimization methodologies.
Normally, intrusions are causes damage to the computer
system resources with the term of unauthorized activities
(modifications) of important files and folders presented
in the system. In [3], especially told information about
intrusion detection and also told its two kinds of
detection principles. There are anomaly detection and
misuse detection. In [4] told methods of classification of
intrusion detection system. Three kinds of methods to be
introduced are audit source location, detection method
and detection paradigm. In audit source location
consider the factors of network packets, application log
files, host log files and IDS sensor alerts. Behaviour and
knowledge based policies are executed using detection
methods. Finally, in detection paradigm to be
considering factors of state based and transition based
detections.
Usually, networking attacks are detecting and preventing
by some classification methods. Normally used
classification methods are svm, genetic and k-NN. Some
of the network intrusion detection and prevention
methods are discussed in [5]. In our proposed system we
have design new the optimal fitness function solution
here; fitness function can be calculated by reward