An improved rule induction based denial of service attacks classification model

For assessing the quality of any internet and cloud computing services; accessibility is presusmed a significant factor among other Quality of Service (QoS) factors. Distributed Denial of Service attack (DDoS) is considered a significant threat pertaining to all contemporary and emerging online-based services. Intelligent solutions centered on the utilization of data mining methods are looming on the horizon as possible solutions to counter this kind of attacks. Rule Induction (RI), which is a well-known data mining method is regarded as a possible approach for developing an intelligent DDoS detection system. The current article offers an “Improved RI algorithm” (IRI) which decreases the searching space for generating classification rules by removing all unimportant candidate rule-items along the way of creating the classification model. The main advantage of IRI is producing a group of rules that can be described as concise, easy to understand, and easy-to-implement. In addition, the classifiers generated by IRI are more compact in size which is heavily weighted when producing any classification system. The proposed algorithm is then applied for detecting DDoS attacks (IRIDOS). Empirical evaluations using the UNSW-NB15 dataset that has been obtained from the University of New South Wales confirmed the robustness of IRIDOS.