About

Andrea Pferscher is a postdoctoral research fellow at the Department of Informatics, University of Oslo. In 2023, she joined the Reliable Systems (PSY) group headed by Einar Broch Johnsen. Her research focuses on the development and application of formal methods for digital twins. She works on two projects related to digital twins: (1) A digital twin for the Oslo Fjord, and (2) A Digital Twin for Vaccination Strategies at Geographic Scales. Additionally, she applies automata learning techniques for the analysis of user behavior.

She did her PhD in 2023 under the supervision of Bernhard K. Aichernig at the Institute of Software Technology at the Graz University of Technology. During her PhD, she focused on automata learning with a particular interest in testing security-critical aspects of black-box systems.

She was a member of the Dependable Internet of Things in Adverse Environments project, whose goal was to improve the dependability of the Internet of Things. In this project, she focused on verified dependability by design. In her master’s thesis, she developed an active learning algorithm for timed systems. In 2019, she joined the project as a PhD student and developed learning-based fuzzing techniques to test IoT protocols like MQTT and Bluetooth Low Energy.

Driven by the challenges of applying active automata learning to test real-world systems, Andrea was a member of the LearnTwins project between 2020 and 2023. The goal of this project is to develop new learning techniques to create digital twins in the form of behavioral models of black-box systems. In collaboration with the Austrian Institute of Technology, she developed a recurrent neural network (RNN) architecture that enables the extraction of a behavioral model from the trained RNN.

Testing and verifying the learned systems was her research focus in the AIDOaRt project. In collaboration with industrial partner AVL, she tested and verified security-critical systems in the automotive domain.