Lorenz Kummer
PhD Candidate in the work group Machine Learning with Graphs

Research Group Data Mining
and Machine Learning
Research and teaching staff
University of Vienna
Währinger Straße 29,
1090 Vienna,
Austria
Room 6.01
Biography
After gaining experience in the IT industry, I transitioned into academia to further my understanding of Computer Science, focusing on machine learning, AI, and modeling. I completed both my Bachelor’s and Master’s degrees at the University of Vienna, graduating with honors in 2022. Alongside my studies, I worked as a research and teaching assistant, which provided valuable practical experience and deepened my theoretical knowledge.
I am currently pursuing a PhD at the University of Vienna, where my research investigates the efficiency, expressivity, and robustness of (graph) neural networks, with a particular focus on adversarial attacks. My work aims to contribute to the theoretical and practical advancements in AI.
Selected Publications
On the Relationship Between Robustness and Expressivity of Graph Neural Networks
Lorenz Kummer, Wilfried Gansterer, Nils Kriege
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics
Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks
Lorenz Kummer, Samir Moustafa, Wilfried Gansterer, Nils Kriege
Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence
Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Leman Go Indifferent
Lorenz Kummer, Samir Moustafa, Sebastian Schrittwieser, Wilfried Gansterer, Nils Kriege
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Adaptive Precision Training (AdaPT): A dynamic quantized training approach for DNNs
Lorenz Kummer, Kevin Sidak, Tabea Reichmann, Wilfried Gansterer
Proceedings of the 2023 SIAM International Conference on Data Mining (SDM)