Intrusion detection and prevention of a malicious activity in a federated cloud computing paradigm

Abstract

The concept of federated cloud computing has reduced the computational cost of an individual user. On the other side, it has increased the security and privacy issues of the information of a cloud client. Users sharing computational resources in a federated cloud can be malicious and can gain access to the sensitive data of users of other cloud providers. Therefore, there is a need to monitor the behavior of consumers, exchanging data between different cloud servers. Using intrusion detection techniques, we can avoid the malicious traffic from gaining an access of the critical data of the clients using cloud services of other cloud providers. Moreover, by adding intrusion prevention technique, we can make our system more robust and efficient. Intrusion Detection and Prevention techniques helped a lot in detecting the malicious activities performed by the intruders. In this domain of securing data, a lot of research is being done. Recently, artificial intelligence and machine learning have greatly attracted the attention of researchers to integrate the concepts of network security with artificial intelligence. In this research, artificial intelligence techniques have been studied and artificial neural network (ANN) model has been finalized to detect the intrusions. Prevention methods are also discussed in this thesis to deploy a properly secured federation in cloud computing environment.