Naive Bayes and SVM based NIDS

In today's world the use of internet services has widely grown. As the number of users has increased the number of attacks on an internet service has also increased exponentially. Although there are a number of intrusion detection systems, ensuring the data security is still a challenging issue. DDoS attacks have been in the networks for a very long time and a large number of hosts are still vulnerable to DDoS attacks. Considering all the scenarios this paper aims at defining a new Intrusion Detection System using statistical behavior and Machine Learning. The proposed approach offers a solution to secure the network resources by using statistical parameters of the flow records for anomaly detection and results in an accurate and efficient system, having a faster response time.