NvCloudIDS: A security architecture to detect intrusions at network and virtualization layer in cloud environment

Abstract

<p>Today we are living in the era of Cloud Computing where services are provisioned to users on demand and on a pay-per-use basis. On oneside, Cloud Computing has made things easier but it has also opened new doors for cyber attackers. In this paper, we propose an efficient security architecture named as NvCloudIDS to deal with intrusions at Network and Virtualization layer in Cloud Environment. NvCloudIDS performs the behavioral analysis of network traffic coming to or going from Cloud Networking Server (CNS) and provides first level of defense from intrusions at network level. It also performs Virtual Machine (VM) memory introspection and VM traffic analysis at hypervsior layer of Cloud Compute Server (CCoS) and provides second level of defense at virtualization level. The architecture of NvCloudIDS is primarily designed to improve the robustness and power of attack detection of IDS by leveraging Virtual Machine Introspection (VMI) and Machine learning techniques. The framework is validated with recent intrusion dataset (UNSW-NB) and malware binaries collected from research centers and the results seem to be promising.</p>