Abstract

While Internet and network technology have been growing rapidly, cyber attack incidents also increase accordingly. The increasing occurrence of network attacks is an important problem to network services. In the recent work present a network based Intrusion Detection and Prevention System DPS, which can efficiently detect many wellknown attack types and can immediately, prevent the network system from Worm attacks. But still many of the network attacks and security threats have been previously reported. Damages caused by network attacks and malware tend to be high. So how to detect different types of network attack becomes very difficult task. However the selection of optimal features for different attacks becomes very difficult task. Some different kinds of intelligent techniques are appropriate for selection of features from network IDPS. In this work we introduce an Adaptive Firefly Algorithm (AFA) for feature selection and classification for intrusion detection in networks based on Unsupervised Fuzzy Extreme Learning Machine (USUFELM) classifier. This proposed approach is simple and efficient and can be used with USUFELM actually implement to IDPS for different attacks. The experimental results show that our IDPS can distinguish normal network activities from main attack types (Probe and Denial of Service) with high accuracy of detection rate in a few seconds and automatically prevent the victim's computer network from the attacks. Surprisingly, the USUFELM be able to work very well, when experiencing with untrained or unknown network attack types.

Paper Details