Majority Vote-Based Ensemble Approach for Distributed Denial of Service Attack Detection in Cloud Computing

Cloud computing is considered as technical advancement in information technology. Many organizations have been motivated by this to outsource their data and computational needs. Such platforms are required fulfil basic security principles such confidentiality, availability, integrity. offers scalable virtualized services with a high flexibility level decreased maintenance costs end-users. The infrastructure protocols that behind cloud may contain bugs vulnerabilities. These vulnerabilities being exploited attackers, leading attacks. Among the most reported attacks distributed denial-of-service (DDOS) DDOS conducted sending many packets targeted infrastructure. This leads network bandwidth server time consumed, thus causing denial of service problem. Several methods proposed experimented for early attack detection. Employing single machine learning classification model give an adequate detection accuracy but needs enhancement. In study, we propose approach based on ensemble classifiers. uses majority vote-based classifiers detect more accurately. A subset CICDDOS2019 dataset consisting 32,000 instances, including 8450 benign 23,550 instances was used study results evaluation. experimental showed 98.02% achieved 97.45% sensitivity 98.65% specificity.