Utilizing Remote Evaluation for Providing Data Sovereignty in Data-sharing Ecosystems

Abstract

The maintenance of digital sovereignty is an important aspect of data-driven business models and data-sharing ecosystems. Considering this, sensitive data is often stored in proprietary systems under the data owner’s control and with appropriate security mechanisms. However, nowadays, it is often necessary to share data. As executing unknown and untrusted code on systems containing sensitive data is potentially dangerous, data-processing algorithms cannot be directly sent to the data-storing systems, as one solution. Instead, we have implemented an approach called remote processing that uses the domain-specific language \degree{}, which provides built-in usage control mechanisms for data processing tasks. The approach extends the well-known remote processing paradigm that allows controlled, distributed data usage without actual data sharing (transmission via network). Instead of classified data, applications and their execution results are transmitted. This way, sensitive data is never directly exposed to third parties. Furthermore, the application-integrated usage control mechanisms prevent malicious data usage.