Improving credibility, Setting up a cloud Intrusion Detection System and Fuzzy Neural Network

Abstract

In the constantly evolving field of cloud computing, ensuring the security and dependability of services is crucial. This research presents a novel method of detecting intrusions in cloud systems using the integration of neural networks with fuzzy logic. The Fuzzy Neural Network Aided Cloud Intrusion Detection System (FNN-CIDS) enhances the precision of identifying malicious activity in cloud settings by using neural network learning capabilities together with the capability of fuzzy systems. The generation is specifically designed to uncover and analyze little patterns that support unwanted access attempts, hence fortifying security protocols for trustworthy cloud-hosted services. The conceptual foundation of FNN-CIDS is described in the study, along with how neural networks are used for pattern reputation and fuzzy common sense is covered for rule-based inference. The results of the trial clearly demonstrate the device's ability to identify different intrusion scenarios while minimizing false positives. This research provides a road map for strengthening cloud computing infrastructure dependability and developing robust security frameworks for cloud-based software applications. The goal of the research paper is to create an intrusion detection system that guarantees there is no unwanted access to cloud services and a trust assessment machine that rates the dependability of cloud services. The self-building clustering algorithm used in the construction of the cloud intrusion detection system is mainly based on neuro-fuzzy techniques. This method's overall performance in cloud intrusion detection has been compared with other well-established clustering algorithms using end-to-end assessment.