Network Traffic Classification-Construction of IDS Using Machine Learning Approaches

Intrusion Detection System (IDS) has been used as a vital instrument in defending the network from this malicious or abnormal activity. it is still desirable to know what intrusions have happened or are happening, so that we can understand the security threats and risks and thus be better prepared for future attacks With the ability to analyze network traffic and recognize incoming and ongoing network attack, majority of network administrator has turn to IDS to help them in detecting anomalies in network traffic In this paper, we focus on different types of attacks on IDS this paper gives a description of different attack on different protocol such as TCP ,UDP,ARP and ICMP. Results show that the detection accuracy of the Genetic based classification accuracy is high at low false-positive-rate on KDD.