A Novel Approach for Classification and Detection of DOS Attacks

Recently internet usage and its users are growing at a tremendous rate. During this growth, having a well secured network is the primary requirement for every organization. To secure a network we need to protect it from the attackers. Websites are a major target of these attackers. Among all the Website attacks, Denial of Service(DOS) attacks are one of the most significant threats to network functionality. DOS attacks exhaust the network's resource of a specific Internet service or system so that the legitimate users lose the access to the resource. DOS attack is an attempt made by the attacker to deny a service to the user. It is an attack that floods the target system with traffic sending malicious information which may crash the system. In our approach we use supervised learning algorithms Support Vector Machine and C4.5 on NSL_KDD Dataset for effective classification of DOS Attack. We use a sniffer for monitoring the network IP Packets and detecting malicious and normal packets from the traffic. Hence, the classifier results are evaluated and best result is displayed.