Analysis and Implementation of the RT-AMD Method for Adaptive DDoS Attack Detection in Cloud Computing Environments

Cloud Computing is a major paradigm in modern computing services that enables the on-demand provision of resources such as servers, storage, and applications over the internet, thereby enhancing efficiency, flexibility, and resource elasticity. Despite these advantages, Cloud Computing infrastructures face significant security challenges, particularly Distributed Denial of Service (DDoS) attacks, which aim to disrupt services by overwhelming systems with high-volume traffic. Several large-scale incidents in 2023 involving global service providers such as Cloudflare, Google Cloud, and Akamai Technologies demonstrate that DDoS attacks are becoming increasingly complex, adaptive, and massive in scale, posing substantial financial and non-financial risks. Numerous previous studies have proposed DDoS detection methods based on machine learning, trust-based models, and intelligent classification techniques; however, many of these approaches still exhibit limitations in handling rapidly evolving attack patterns in dynamic cloud environments. Therefore, more adaptive and responsive detection mechanisms are required. This research aims to analyze and implement an adaptive DDoS attack detection system using the Real-Time Attack Monitoring and Detection (RT-AMD) method in Cloud Computing infrastructures. By leveraging real-time traffic monitoring and machine learning-based analysis, RT-AMD is expected to effectively identify suspicious activities, improve detection accuracy, accelerate mitigation responses, and ultimately enhance the reliability and security of Cloud Computing services.