A SURVEY ON DETECTION OF DENIAL OF SERVICE ATTACK

Denial-of-Service attack is an attempt to make network resources or machine unavailable to its intended users. It can temporarily or indefinitely interrupt or suspend the services of a host connected to the Internet. For the Detection of denial of service attack (DoS) various detection systems are developed. The existing method is based on machine learning and statistical analysis, the proposed system changes the traffic records as images and detection of DoS attacks as a computer vision problem. In this proposed method a multivariate correlation analysis approach is developed to explain network traffic records and changes the records into the respective images. Network traffic records images are used for the proposed denial of service attack detection system that is developed based on a dissimilarity measure Earth Mover’s Distance. By using this method it can also detect the unknown Denial of Service attack. KEYWORDS:Denial of service attack (DoS), Earth mover’s distance, Machine learning, Statistical learning