Curriculum Vitae

Lukas Koller joined the Cyber-Physical-Systems Group as a Ph.D. candidate under the supervision of Prof. Dr.-Ing. Matthias Althoff in late 2023. Lukas has received both, his master's degree and his bachelor's degree in Informatics from the Technical University of Munich in 2023 and 2021, respectively.

His research interests include formal verification of neural networks and training of robust neural networks. He is a member of the DFG-funded project "Data-driven process modelling in metal forming technology".

Offered Thesis Topics

I am always looking for self-motivated students who want to work in my research area. If you are interested in writing your thesis in the field of my research, please write me an email containing your CV, transcript of records, and a rough direction you are interested in. Check the thesis proposals and practical course topics below for examples.

Ongoing:

• [BT] Exploiting Monotonicity for Training and Verification of Neural Networks
• [MT] Set-Based Learning of Neural Barrier Certificates for Safety Verification of Dynamic Systems

Finished:

• [BT] Robust Reinforcement Learning using Set-Based Training
• [BT] Evaluating the Robustness of Neural Networks with Adversarial Attacks

Teaching

Practical Course – Verification, Controller Synthesis, and Design of Cyber-Physical Systems (IN2106, IN4269)

• Implementation of algorithms for formal neural network verification in CORA [WiSe 23/24: Topics] [SoSe 24: Topics]

Seminar – Cyber-Physical Systems (IN0014, IN2107, IN4813)

• Literature research on training robust neural networks [SoSe 24: Topics]

Lecture – Formal Methods for Cyber-Physical Systems (IN2383) [WiSe 23/24] [WiSe 24/25]