HYBRID MACHINE LEARNING APPROACH FOR DDOS DETECTION IN CLOUD COMPUTING WITH REAL-TIME PERSPECTIVE

Cloud computing has revolutionized the IT industry by providing scalable and cost-effective services. However, it is highly vulnerable to Distributed Denial of Service (DDoS) attacks, which can disrupt service availability. This paper proposes a hybrid machine learning approach for detecting DDoS attacks in cloud environments. The proposed model integrates Random Forest, NaIve Bayes, and XG Boost algorithms to improve detection accuracy. The system is evaluated using standard datasets, and performance metrics such as accuracy, precision, and recall are analyzed. Furthermore, the model is designed with the potential for real-time implementation. Experimental results demonstrate that the hybrid model outperforms individual classifiers, making it suitable for secure cloud environments.