An Adaptive Framework for Low-Rate DDoS Detection in Cloud Environments Using Decision Tree Machine Learning Algorithm

An adaptive detection framework to identify low-rate Distributed Denial of Service (DDoS) attacks in cloud environments. Leveraging the Decision Tree machine learning algorithm, the framework offers a proactive approach to identifying and mitigating these attacks. By adapting to the dynamic nature of cloud environments, the framework enhances detection accuracy while minimizing false positives. Through experimentation and evaluation, the efficacy of the proposed approach is demonstrated, showcasing its potential to bolster security measures in cloud infrastructures against DDoS threats. Low-rate DDoS attacks make detection particularly difficult. Meanwhile, cloud infrastructure is rapidly evolving with container-based technology allowing efficient resource utilization and flexible service scaling. Existing methods for detecting DDoS attacks in cloud computing are insufficient against low-rate DDoS attacks, requiring a method capable of both identifying and preventing them to some extent. The Adaptive Framework is designed specifically for cloud environments, considering the dynamic nature of cloud infrastructure and the necessity for scalable and efficient detection mechanisms. The core detection mechanism relies on a Decision Tree Machine Learning Algorithm known for its framework offers high interpretability and can effectively process both categorical and numerical data. Decision trees partition the data based on features, making them suitable for capturing patterns in network traffic indicative of low-rate DDoS attacks. The framework likely accommodates the scalability requirements of cloud environments, given the dynamic scaling of resources inherent in cloud computing.