Cyber Times International Journal of Technology & Management

In recent years, due to rapid increase of network applications the data and privacy security in network is a key challenge. In order to provide effective and trustable security for network, intrusion detection systems are helpful technique. The presented survey is based on the IDS system design for network based anomaly detection. Thus this system requires an efficient and appropriate classifier by which the detection rate of intrusions using KDD CUP dataset can be improved. There are various data mining based classification and pattern detection techniques are available. These techniques are promising for detecting network traffic pattern more accurately. On the other hand recently developed combined models are providing more accurate classification. Thus an intrusion detection system model based on neural network using Bayesian and KPCA is presented. The given approach will help to filter the attributes and data instances that misguide the classification. Therefore, a data mining algorithm for an intrusion detection system model based on neural network using Bayesian and KPCA is employed for improving data quality and classification improvement. The implementation of the modified classification system will be performed using JAVA environment and performance of classification will be evaluated.