Research Interests
A more comprehensive overview on my research (interests) can be found on my personal homepage: www.teuber.dev- Formal Methods for Machine Learning in the context of topics like:
- Neural Network Verification
- Verification of ML-enabled Cyber-Physical Systems
- Algorithmic Fairness
- Quantitative Verification of Software
Publications
| Titel | Autor(en) | Quelle |
|---|---|---|
| Verification of Autonomous Neural Car Control with KeYmaera~X | Enguerrand Prebet, Samuel Teuber und André Platzer | Rigorous State-Based Methods - 11th International Conference, ABZ 2025, Düsseldorf, Germany, Proceedings |
| Next Steps in LLM-Supported Java Verification | Samuel Teuber und Bernhard Beckert | 2025 IEEE/ACM 1st International Workshop on Neuro-Symbolic Software Engineering (NSE) |
| Of Good Demons and Bad Angels: Guaranteeing Safe Control under Finite Precision | Samuel Teuber, Debasmita Lohar und Bernhard Beckert | 2025 Formal Methods in Computer-Aided Design (FMCAD) |
| Revisiting Differential Verification: Equivalence Verification with Confidence | Samuel Teuber, Philipp Kern, Marvin Janzen und Bernhard Beckert | TACAS |
| Titel | Autor(en) | Quelle |
|---|---|---|
| Towards Combining the Cognitive Abilities of Large Language Models with the Rigor of Deductive Progam Verification | Bernhard Beckert, Jonas Klamroth, Wolfram Pfeifer, Patrick Röper und Samuel Teuber | 12th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation (ISoLA 2024). Software Engineering Methodologies |
| Quantifying Software Correctness by Combining Architecture Modeling and Formal Program Analysis | Florian Lanzinger, Christian Martin, Frederik Reiche, Samuel Teuber, Robert Heinrich und Alexander Weigl | Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, SAC 2024 |
| An Information-Flow Perspective on Algorithmic Fairness | Samuel Teuber und Bernhard Beckert | Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, The Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2024, Vancouver, BC, Canada, February 20 - February 27, 2024 |
| Provably Safe Neural Network Controllers via Differential Dynamic Logic | Samuel Teuber, Stefan Mitsch und André Platzer | Advances in Neural Information Processing Systems |
| Titel | Autor(en) | Quelle |
|---|---|---|
| Formally Verified Algorithmic Fairness Using Information-Flow Tools | Samuel Teuber und Bernhard Beckert | Proceedings of the 2nd European Workshop on Algorithmic Fairness, Winterthur, Switzerland, June 7th to 9th, 2023 |
| Titel | Autor(en) | Quelle |
|---|---|---|
| The counterSharp Model Counting Benchmark | Samuel Teuber und Alexander Weigl | Karlsruhe Institute of Technology 2022-02 |
| Titel | Autor(en) | Quelle |
|---|---|---|
| Geometric Path Enumeration for Equivalence Verification of Neural Networks | Samuel Teuber, Marko Kleine Büning, Philipp Kern und Carsten Sinz | 33rd IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2021) |
| Quantifying Software Reliability via Model-Counting | Samuel Teuber und Alexander Weigl | 18th International Conference on Quantitative Evaluation of Systems (QEST 2021) |
| Titel | Autor(en) | Quelle |
|---|---|---|
| An Incremental Abstraction Scheme for Solving Hard SMT-Instances over Bit-Vectors | Samuel Teuber, Marko Kleine Büning und Carsten Sinz | CoRR abs/2008.10061 |
| Titel | Autor(en) | Quelle |
|---|---|---|
| Efficient unpacking of required software from CERNVM-FS | Samuel Teuber | Zenodo 2019-02 |