A data mining based approach towards detection of low rate DoS attack

Low rate Denial of Service attack is an advanced form of DoS attack which has high concealment characteristics due to its behaviour like normal traffic. Due to this characteristics of LDoS, currently available tools and IDS have very low efficiency in detection of LDoS attacks and hence these attacks are successful in thwarting legitimate users from accessing the network resources. Most of the researchers propose to make changes in protocols, router, network configuration, node functionalities and network topography in their proposed solution which is highly impractical. This paper presents a data mining based approach for detection of LDoS attack without making any changes in the network environment. Experimental results are provided to support the proposed mechanism.