Enhancing Cloud Security with Trusted Execution

The increasing popularity of cloud computing also leads to a growing demand for security guarantees in cloud settings. Cloud customers want to be able to execute sensitive data processing in clouds only if a certain level of security can be guaranteed to them despite the unlimited power of the cloud provider over her infrastructure. However, security models for cloud computing mostly require the customers to trust the provider, its infrastructure and software stack completely. While this may be viable to some, it is by far not to all customers, and in turn reduces the speed of cloud adoption. In this thesis, the applicability of trusted execution technology to increase security in a cloud scenario is elaborated, as these technologies are recently becoming widespread available even in commodity hardware. However, applications should not naively be ported completely for usage of trusted execution technology as this would affect the resulting performance and security negatively. Instead they should be carefully crafted with specific characteristics of the used trusted execution technology in mind. Therefore, this thesis first comprises the discussion of various security goals of cloud-based applications and an overview of cloud security. Furthermore, it is investigated how the ARM TrustZone technology can be used to increase security of a cloud platform for generic applications. Next, securing standalone applications using trusted execution is described at the example of Intel SGX, focussing on relevant metrics that influence security as well as performance of such an application. Also based on Intel SGX, in this thesis a design of a trusted serverless cloud platform is proposed, reflecting the latest evolution of cloud-based applications.