Projects

Our research group develops a framework for serverless scientific computing to make large-scale Earth observation (EO) workflows more reusable, reproducible, and accessible. By combining computer science, geosciences, and ecology, we aim to automate and simplify the processing of petabyte-scale, heterogeneous satellite and environmental data—removing technical barriers for researchers. This interdisciplinary approach opens new opportunities to study pressing sustainability questions, from climate impacts on snow cover to biodiversity shifts driven by land surface dynamics.

MicroGenerator is a novel framework designed to unlock the potential of transfer learning for microservice architectures. By automating the creation and benchmarking of synthetic microservice applications using a library of reusable building blocks, it addresses the lack of large training datasets—a key barrier to applying transfer learning in areas like autoscaling, energy-efficient placement, and resource saturation detection.

The IoTGuard project, in collaboration with partners TU Darmstadt, Intel, Kobil, and IoT-Venture, develops AI-driven security for smart homes. Despite IoT excitement, challenges in device diversity and adversarial attacks persist. IoTGuard focuses on addressing these issues, emphasizing smart home security, distributed learning, and context-based attack detection. Insights are expected to apply in critical environments beyond smart homes. Project of the German Federal Ministry of Education and Research.

The Minerva project focuses on predicting both transient and steady-state performance of microservice applications in container orchestration environments, such as those managed by Kubernetes. By developing new models, simulation algorithms, and benchmarks, as well as treating adaptation mechanisms of container orchestration frameworks as black-boxes, it aims to provide comprehensive and tangible insights into system behaviors and optimization opportunities.

ROOT is an interdisciplinary research project funded by the bidt of the Bavarian Academy of Science and aims to develop a geoinformation portal that can provide timely and targeted information on forest dynamics, local damage events, and biodiversity changes based on satellite data for the entire Bavaria region.

The main challenge for IoT developers is the lack of a unified security solution that can work across a variety of different devices. To bridge this gap, the CROSSCON project pools the expertise of 11 research teams throughout Europe to develop a new open and vendor-independent security stack for connected devices. The CROSSCON security stack provides a consistent security baseline across a whole IoT system.

Smart Contracts are computer programs that execute on a blockchain. The nature of blockchains allows one to run Smart Contracts in a trustless and decentralized environment. In this project, we demonstrate the effectiveness of Deep Neural Networks in the domain of Smart Contract vulnerability detection.

Marie Skłodowska-Curie Actions Staff Exchange Project founded by the European Union

The main challenge for IoT developers is the lack of a unified security solution that can work across a variety of different devices. To bridge this gap, the CROSSCON project pools the expertise of 11 research teams throughout Europe to develop a new open and vendor-independent security stack for connected devices. The CROSSCON security stack provides a consistent security baseline across a whole IoT system.