Identification of network intrusion with efficient Genetic Algorithm using Bayesian classifier

In the field of computer security, the intrusion detection system plays a major role. Whenever the intrusion takes place, intrusion detection technology is used to ensure the data integrity and system availability. Normally the intrusion is considered as an abnormal activity performed by the intruder. The breaking of information system or occurrence of any abnormal activity if performed by the intruder is known as intrusion. Based on the nature of access the intruders can be broadly classified into two groups, as internal intruders and external intruders. One who is having the access permission but trying to perform unauthorized or illegal activities is known as internal intruders. On the other hand one who do not have the access permission, but attacks the system with variety of techniques is called identified as external intruders. The IDS is a security management system for the computers and networks. It helps in monitoring and detecting all the activity which takes place in the Network. On consideration, the firewall technology works on the predetermined rule set. In contrast to this, IDS is potential to be present throughout the network as dynamic defense system. Hence it helps to catch all types of attacks. Genetic Algorithms (GA) is a method of search through solution space towards an optimal solution that uses the mechanics of natural selection and genetics. The main motivating factor for using GA is that it makes no use of domain knowledge; it works on probabilistic techniques making use of payoff data. Another huge advantage that GA has over other learning systems is that GA is totally unsupervised, once set in motion, it presents the user with a good solution. These coupled with the versatility and robustness of GA makes the technique of choice for this work. This research work focus on applying the Genetic Algorithm (GA) based on the classifiers to network Intrusion Detection Systems (IDS). Unlike the other implementations, both temporal and spatial enc- ding information is considered here. It helps in identifying the complex behavior patterns.