An Experiential Metrics-Based Machine Learning Approach for Anomaly Based Real Time Prevention (ARTP) of App-DDoS Attacks on Web

Abstract

The Internet is often victimized to the distributed denial of service (DDoS) attack, in which purposefully occupies the bandwidth and computing resources in order to deny that services to potential users. The attack situation is to flood the packets hugely to the target system. If the attack is from a single source, then the attack is called as denial of service (DoS) and if attack is from divergent servers, then it is called as DDoS. Over a decade, several researchers succeeded to deliver few significant DDoS detection and prevention strategies by considering the detection and prevention of DDoS attack as research objective. In present level of Internet usage, “how fast and early detection of DDoS attack” is done in streaming network transactions which is still a significant research objective. Unfortunately, the current benchmarking DDoS attack detection strategies are failed to justify the objective called “fast and early detection of DDoS attack.” In order to this, we devised an anomaly based real time prevention (ARTP) of application-layer DDoS attacks (App-DDoS attacks) on Web that is in the aim of achieving fast and early detection. The ARTP is a machine learning approach that is used to achieve the fast and early detection of the App-DDoS by multitude request flood. The experiments were carried out on benchmarking LLDoS dataset, and the results delivered are boosting the significance of the proposed model to achieve the objective of the paper.