Double Reinforcement Learning Based Interactive GAN for Detection of Volumetric Attacks in Cloud Computing

The rapid growth of cloud computing has increased the risk of volumetric attacks on cloud infrastructure. This research paper proposes a comprehensive approach to detect such attacks in cloud environments. The methodology combines Double Reinforcement Learning (DRL) and Interactive Generative Adversarial Networks (GANs) to improve anomaly detection accuracy and efficiency. DRL enables dynamic adaptation of detection capabilities, while GANs generate realistic synthetic data for training and evaluation. Experimental results show that the proposed approach accurately identifies and classifies volumetric attacks with lower false positives and negatives compared to existing methods. This solution holds promise for enhancing the security and resilience of cloud computing against volumetric attacks.