Securing Open Source Clouds Using Models

Abstract: The widespread adoption of cloud computing has resulted in the proliferation of open source cloud computing frameworks that give more control to enterprises over their data and networks. Though the benefits of open source software are widely recognized, there is a growing concern over their security assurance. Often open source software is a subject of frequent updates. The updates might introduce or remove a variety of features and hence violate security properties of the previous releases. Obviously, a manual inspection of security would be prohibitively slow and inefficient. In this work, we propose an automated approach that can help developers to assure the security of open source cloud framework even in the presence of frequent releases. Our methodology consists of creating a (stateful) wrapper that emulates the usage scenarios with explicit representation of security and functional requirements as contracts. We use a model-driven approach to model REST APIs of KeyStone, an identity service in OpenStack. OpenStack is an open source cloud computing framework providing IaaS. Our models define structural and behavioral properties of Keystone together with its security requirements. We detail the implementation of these models in Django Web Framework and also show how to use the behavioral interfaces to implement a service monitor for the cloud services. This mechanism facilitates verification and validation of functional behavior and security requirement in an automated manner.