SS-DDoS:
Nilesh Vishwasrao Patil, Cettymalla Rama Krishna, Krishan Kumar · 2022
A Distributed Denial of Service (DDoS) attack is a critical threat to web-based systems and overwhelms systems by transferring a large number of attack packets. Several classification approaches have been proposed in the literature to provide solutions for web-based systems from different kinds of DDoS attacks. However, DDoS attack occurrences are growing year after year. Furthermore, few problems exist in the existing classification approaches, such as itself becoming the victim of attacks, requiring more time for classification, and no real-time replies to incoming traffic. Therefore, existing classification approaches are not competent in classifying incoming network traces in real time. In this chapter, we propose Spark Streaming-based DDoS classification approach named SS-DDoS. The proposed SS-DDoS is designed using the distributed Spark MLlib by employing the K-Means clustering algorithm. The chapter then discusses K-Means clustering-based classification model on the Spark Streaming Cluster. The results show that the proposed SS-DDoS classification approach efficiently classifies incoming network traces in real time.