Intrusion Detection Techniques Based Secured Data Sharing System for Cloud Computing Using MSVM

Abstract

Cloud storage has grown in popularity, attracting a lot of interest from academics and IT professionals. In the digital era, cloud computing has grown increasingly vital for scalable resource sharing, smooth computing, and information interchange. Researchers have a challenging task in securing cloud data, resources, applications, and infrastructure. Cloud security methods are used to protect the cloud in the cloud computing environment. Detective controls, for example, are critical in cloud security because they discover possible breaches and defend the cloud environment from attacks. This detective control mechanism is built using an intrusion detection system (IDS). The network traffic data utilised to build the IDS using a machine-learning algorithm has a major influence on the detection accuracy of the IDS. When the performance of the proposed algorithm is compared to that of existing algorithms, it is observed that the new approach outperforms the others. Intrusion detection systems (IDS) have become an important security tool for monitoring and researching network security in mobile cloud computing (MCC). However, several modern techniques still have flaws, such as high false positive rates, poor classification accuracies, and low true positive rates. This paper provides an intrusion detection strategy for MCC based on support vector machines (SVM) and information gain (IG). The suggested approach employs the SVM classifier to categories network data into normal and attack behaviours, and IG to choose the significant features and reduce the unnecessary features, because to the irrelevant and duplicated characteristics seen in KDD datasets. Because it can be accessible from anywhere on the internet, cloud storage has become the most popular data and information storage option. While it has its own set of advantages and benefits, its storage system protection has certain drawbacks. Cloud encryption ensures that cloud storage is secure, but it does not guarantee that the system will not be hacked. Cloud storage, like any other untrustworthy setting, demands the ability to safeguard shared data. This suggested solution gives access control to data handled in the cloud without contacting the vendor.