Privacy-Friendly Cloud Audits with Somewhat Homomorphic and Searchable Encryption

In this paper, we provide privacy enhancements for a software agent-based audit system for clouds. We also propose a general privacy enhancing cloud audit concept which, we do present based on a recently proposed framework. This framework introduces the use of audit agents for collecting digital evidence from different sources in cloud environments. Obviously, the elicitation and storage of such evidence leads to new privacy concerns of cloud customers, since it may reveal sensitive information about the utilization of cloud services. We remedy this by applying Somewhat Homomorphic Encryption (SHE) and Public-Key Searchable Encryption (PEKS) to the collection of digital evidence. By considering prominent audit event use cases we show that the amount of cleartext information provided to an evidence storing entity and subsequently to a third-party auditor can be shaped in a good balance taking into account both, i) the customers' privacy and ii) the fact that stored information may need to have probative value. We believe that the administrative domain responsible for an evidence storing database falls under the adversary model "honest-but-curious" and thus should perform query responses from the auditor with respect to a given cloud audit use case by purely performing operations on encrypted digital evidence data.