Hello!

I am a PhD student (supervised by Prof. Martin Lange) and part of the Formal Methods / Theoretical Computer Science group at the University of Kassel, Germany.

Research

Currently, my research interests lie in the interface between formal methods and machine / deep learning. In particular, I am currently working on understanding the computational complexity of formal reasoning tasks for various neural network based models, like feedforward neural networks, graph neural networks or transformers.

News

• Our work “Verifying and interpreting neural networks using finite automata” (M.S., E. Alsmann, F. Bruse, M. Lange) got accepted to DLT 24 in Goettingen, (May 24).
• Our work “A Logic for Reasoning About Aggregate-Combine Graph Neural Networks” (P. Nunn, M.S., F. Schwarzentruber, N. Trouquard) got accepted to IJCAI 24 in Jeju, (April 2024).
• I presented our current work on GNN verification at the LoG Local Meetup 23 in Munich, (November 23).
• I gave an invited talk surveying results on the computational complexity of reachability properties of FNN, GNN and Transformer at the 68nqrt seminar in Rennes, (November 23).
• I gave a talk on our work on the complexity of GNN verification at HIGHLIGHTS 23 in Kassel, (July 23).
• Together with one of our master students, I presented our current work on DNN to NFA translation at LiVe 23 in Paris, (April 23).
• I gave a talk about our work on the complexity of GNN verification at the Doctoral Symposium located at FM 23 in Luebeck, (March 23).
• I gave a talk about our work on the complexity of GNN verification at AlMoTh 23 in Bochum, (March 23)