Distributed denial-of-service attack detection and mitigation using feature selection and intensive care request processing unit

Worldwide acceptance of cloud computing is increasing day by day because it provides large amount of IT resources in a very simplified and economic manner. Cloud provides high security to its customers, but still there are some vulnerabilities present in cloud that attracts many attackers. Distributed denial-of-service (DDoS) attack is one of the nightmares for many cloud providers which affects the availability of resources in cloud network. This paper proposes a DDoS attack detection and mitigation model using the feature selection method and Intensive Care Request Processing Unit (ICRPU). In the proposed work, initially traffic is analyzed using Hellinger distance function, and if some distance is found, then all the packets are analyzed and classified in two categories, as DDoS and legitimate request groups on the basis of feature selected for the classification. The entire legitimate requests are forwarded to Normal Request Processing Unit where these request could be completed. All the DDoS request are sent to ICRPU were these request got busy in question and answer and in parallel source of these request are identified and blocked for further access. The specialty of ICRPU is that the attacker will never realize that the request sent by them to exhaust the resources are trapped, so the attacker will not perform any reflex action, and it becomes easy to track the attacker. Results shows that the proposed method provides the best detection rate, accuracy, and false alarm in comparison with existing filter methods and other such proposed method.