Hybrid SVM Approach for Enhanced DDoS Attack Detection Using Machine Learning in Cloud Environment

Cloud computing's popularity is on the rise, attracting a select number of organizations investing in this realm, either for internal use or to serve others. However, this surge in cloud innovation has led to the emergence of fresh security concerns impacting both customers and the industry. To address these challenges, machine learning (ML) has been increasingly employed in cloud systems. ML techniques have found application in various contexts, aiming to pre-emptively detect and mitigate potential attacks and vulnerabilities within the Cloud. Our study presents a Systematic Literature Review (SLR) delving into security protocols and strategies at the intersection of cloud technology and machine learning. Examining 63 significant studies, our SLR findings are classified into three principal research domains: (I) the diverse array of security threats prevalent in Cloud computing, (ii) the spectrum of machine learning techniques utilized, and (iii) the resulting outcomes and implications of these methodologies. Moreover, distributed denial-ofservice (DDoS) and information security stand out as the most prominent Cloud security domains, accounting for 16% and 14% of usage, respectively. In our analysis, we discovered that 30 distinct ML methods employed a combination of both independent and pre-existing hybrid strategies.