Securing Cloud Networks: A Hybrid Intrusion Detection Approach Using Fuzzy C-Means Clustering and Decision Tree Classification

Cloud computing has emerged as a pivotal technology for efficient data management and resource provisioning, leveraging internet connectivity to offer a broad range of services from basic storage and networking to advanced functionalities like natural language processing and artificial intelligence. However, this pervasive adoption also exposes cloud environments to significant cybersecurity threats. Denial of Service (DoS) attacks, data hijacking, information theft, and bandwidth consumption attacks pose serious risks, necessitating robust security functionalities. Intrusion Detection Systems (IDSs) help in mitigating these threats by tracking network behavior and system activities for suspicious behavior. Traditional IDS approaches often rely on machine learning algorithms such as Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Random Forests (RFs), and Naïve Bayes (NB), but these methods face challenges in effectively handling cloud-specific nuances. Therefore we present a hybrid IDS framework integrating the Fuzzy C-Means (FCM) clustering algorithm and decision tree classifier, called FCM-DT, to enhance detection accuracy while minimizing false alarms. FCM-DT is evaluated using the NSL-KDD dataset, indicating superior performance in comparison to traditional approaches. This study contributes to advancing intrusion detection capabil-ities in cloud environments, aiming to bolster security measures against evolving cyber threats.