A Neuro Fuzzy Based Intrusion Detection System for a Cloud Data Center Using Adaptive Learning

With its continuous improvements, the cloud computing system leaves an open door for malicious activities. This promotes the significance of constructing a malware action detection component to discover the anomalies in the virtual environment. Besides, the traditional intrusion detection system does not suit for the cloud environment. So, the proposed scheme develops an anomaly detection system, named Hypervisor Detector at a hypervisor layer to detect the abnormalities in the virtual network. Besides, the fuzzy systems have the ability to detect the presence of uncertain and imprecise nature of anomalies; they are not able to construct models based on target data. One of the successful approaches, which integrate fuzzy systems with adaptation and learning proficiencies of a neural network, such as ANFIS (Adaptive Neuro Fuzzy Inference System) model, is based on target values. The Hypervisor Detector is designed and developed with an ANFIS and practised with a hybrid algorithm, a combination of the back propagation gradient descent technique with the least square method. For the experiments and performance analysis, DARPA’s KDD cup data set is used. The performance analysis and results show that the model proposed is well designed to detect the abnormalities in virtual environment with the minimum false alarm rate and reduced overhead.