Enhancing Network Security using Hybrid Machine Learning Techniques

Intrusion detection is a crucial tool for establishing a safe and reliable Network computing environment, considering the widespread and ever-changing nature of cyber threats. Network Computing offers a substantial enhancement in cost metrics by dynamically providing IT services inside our present framework of resource, platform, and service consolidations. Given that the majority of cloud computing networks rely on delivering their services via the Internet, they are susceptible to encountering a range of security concerns. Hence, it is imperative to implement an Intrusion Detection System (IDS) in cloud settings to effectively identify novel and unfamiliar threats, alongside established signature-based attacks, with a notable level of precision. In the course of our analysis, we make the assumption that a "anomalous" event in a system or network is equivalent to a "intrusion" event, which occurs when there is a substantial deviation in one or more fundamental activities of the system or network. Several recent proposals have been put out with the objective of creating a hybrid detection mechanism that combines the benefits of signature-based detection techniques with the capability to identify unfamiliar assaults through anomalies. This study presents a novel anomaly detection system at the Network, the virtual machine level, which incorporates a hybrid algorithm. The technique combines the Naive Bayes algorithm and the SVM classification algorithm with k-Means clustering. The objective is to enhance the accuracy of the anomaly detection system. In regard to the general effectiveness in terms of detection rate and low false positive rate, the results of this study indicate that the suggested solution outperforms the traditional models.