AN ARTIFICIAL INTELLIGENCE TECHNIQUE FOR A PROACTIVE MULTI-CLOUD COOPERATIVE INTRUSION DETECTION SYSTEM

The increasing adoption of multi-cloud architectures has introduced significant security challenges due to the distributed and dynamic nature of cloud environments. Traditional intrusion detection systems (IDS) are largely designed for single network infrastructures and struggle to provide consistent and accurate threat detection across multiple cloud platforms. This paper presents a proactive intrusion detection system using Convolutional Neural Networks (CNNs) deployed across a cooperative multi cloud environment using Kubernetes orchestration. The proposed system is implemented on Amazon Web Services Elastic Kubernetes Service (AWS EKS) and Microsoft Azure Kubernetes Service (Azure AKS), enabling scalable and platform agnostic intrusion detection. Network traffic data from the CICIDS2017 dataset is used to train and evaluate the CNN model. Experimental results demonstrate that the proposed IDS achieves an accuracy of 99.59%, with high precision and recall, indicating strong capability in detecting both known and novel attacks. The integration of Kubernetes enables seamless deployment, scalability, and resilience across cloud providers. The findings demonstrate that combining deep learning with container orchestration provides an effective and practical approach to securing modern multi cloud infrastructures.