A New Framework for Anomaly Detection in NSL-KDD Dataset using Hybrid Neuro-Weighted Genetic Algorithm

There are an increasing number of security threats to the Internet and computer networks. For new kinds of attacks constantly emerging, a major challenge is the development of versatile and innovative security-oriented approaches. Anomaly-based network intrusion detection techniques are in this sense a valuable tool for defending target devices and networks from malicious activities. With testing dataset, this work was able to use the NSL-KDD data collection, the binary and multiclass problems. With that inspiration, data mining techniques are used to offer an automated platform for network attack detection. The system is based on the Hybrid Genetic Neuro-Weighted Algorithm (HNWGA).In this weighted genetic algorithm is used for the selection of features and in this work a neuro-genetic fuzzy classification algorithm has been proposed which is used to identify malicious users by classifying user behaviors. The main benefit of this proposed framework is that it reduces the attacks by highly accurate detection of intruders and minimizes false positives. The evaluation of the performance is performed in NSL-KDD dataset. The experimental result shows of that the proposed work attains better accuracy when compared to previous methods. Such type of IDS systems are used in the identification and response to malicious traffic / activities to improve extremely accuracy.