Postdoctoral research fellow at the Department of Informatics, University of Oslo.
Our paper Mining Digital Twins of a VPN Server has been presented at the workshop Applications of Formal Methods and Digital Twins in Lübeck, Germany.
In this paper, written together with Benjamin Wunderling, Bernhard K. Aichernig, and Edi Muškardin, we showcase how active automata learning can be used to mine digital twins of VPN servers.
Together with our industrial project partner AVL, we won the 3rd edition of the AIDOaRt hackathon.
In our presented hackathon challenge, we learning-based fuzzed the Bluetooth Low Energy interface of Automotive Grade Linux (AGL). For this purpose, we simulated the software components of a vehicle with AGL. You find more information in this article.
Our paper Constrained Training of Recurrent Neural Networks for Automata Learning has been presented at SEFM’22 in Berlin.
In this paper, written together with Bernhard K. Aichernig, Sandra König, Cristinel Mateis, Dominik Schmidt, and Martin Tappler, we propose a recurrent neural network architecture that enables the learning of a finite automata.