Comprehensive Examination of Learning-based DDoS Defence Methods for Cloud Computing Networks

Abstract

Cloud computing can be a valuable resource; data storage, software, infrastructure, and platform services are just a few of the perks of cloud computing. The majority of cloud services are executed through Internet connection and thus they are susceptible to a large extent of attacks that can lead to disclosure of sensitive information. Malicious activities such as distributed denial-of-service (DDoS) attacks are immediately threatening the cloud environment and the services offered to the bona fide users. This study examines the various machine learning (ML)-based, deep learning (DL)-based, and Reinforcement Learning (RL) DDoS detection methods used across different cloud environments. The primary goal of this literature review paper is to provide a comprehensive analysis of the existing literature regarding the latest trends in advanced flooding attack detection and intrusion detection systems (IDS) approaches used for defending cloud computing networks. The review is limited to the papers that have been published between 2016 and 2023 addressing methods of flood or DDoS defense for cloud computing networks. It focuses on the advanced learing-based DDoS detection techniques based on ML, DL, RL. It also describes other forms of flooding attacks and the testing dataset. Finally, it identifies a number of research issues, limitations, and directions for further research in the context of DDoS attack detection and prevention in cloud computing networks.