Publications

2026

  1. icml_26.jpg
    Efficient and Safe Molecular Assembly via Reinforcement Learning and Constraint Solving
    Stefan Pranger, Bernhard Ramsauer, Oliver T. Hofmann, and Bettina Könighofer
    In 43rd International Conference on Machine Learning ICML, 2026
    To appear

2025

  1. Explainably Safe Reinforcement Learning
    Sabine Rieder, Stefan Pranger, Debraj Chakraborty, Jan Kretinsky, and Bettina Könighofer
    In 39th Advances in Neural Information Processing Systems NeurIPS, 2025
  2. Fairness Shields: Safeguarding against Biased Decision Makers
    Filip Cano, Thomas A. Henzinger, Bettina Könighofer, Konstantin Kueffner, and Kaushik Mallik
    In 39th Conference on Artificial Intelligence AAAI, 2025
  3. Shields for Safe Reinforcement Learning
    Bettina Könighofer, Roderick Bloem, Nils Jansen, Sebastian Junges, and Stefan Pranger
    Communication of the ACM, 2025

2024

  1. soid: A Tool for Legal Accountability for Automated Decision Making
    Samuel Judson, Matthew Elacqua, Filip Cano, Timos Antonopoulos, Bettina Könighofer, Scott J. Shapiro, and Ruzica Piskac
    In 36th International Conference on Computer Aided Verification CAV, 2024
  2. ’Put the Car on the Stand’: SMT-based Oracles for Investigating Decisions
    Samuel Judson, Matthew Elacqua, Filip Cano, Timos Antonopoulos, Bettina Könighofer, Scott J. Shapiro, and Ruzica Piskac
    In 3rd Symposium on Computer Science and Law CSLAW, 2024
  3. Abstraction-Based Decision Making for Statistical Properties (Invited Talk)
    Filip Cano, Thomas A. Henzinger, Bettina Könighofer, Konstantin Kueffner, and Kaushik Mallik
    In 9th International Conference on Formal Structures for Computation and Deduction FSCD, 2024
  4. Learning and Repair of Deep Reinforcement Learning Policies from Fuzz-Testing Data
    Martin Tappler, Andrea Pferscher, Bernhard K. Aichernig, and Bettina Könighofer
    In 46th International Conference on Software Engineering ICSE, 2024
  5. Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
    Stefan Pranger, Hana Chockler, Martin Tappler, and Bettina Könighofer
    In 38th Annual Conference on Neural Information Processing Systems NeurIPS, 2024
  6. Learning Environment Models with Continuous Stochastic Dynamics - with an Application to Deep RL Testing
    Martin Tappler, Edi Muskardin, Bernhard K. Aichernig, and Bettina Könighofer
    In 17th Conference on Software Testing, Verification and Validation ICST, 2024

2023

  1. Analyzing Intentional Behavior in Autonomous Agents under Uncertainty
    Filip Cano Córdoba, Samuel Judson, Timos Antonopoulos, Katrine Bjørner, Nicholas Shoemaker, Scott J. Shapiro, Ruzica Piskac, and Bettina Könighofer
    In 32nd International Joint Conference on Artificial Intelligence IJCAI, 2023
  2. Safety Shielding under Delayed Observation
    Filip Cano Córdoba, Alexander Palmisano, Martin Fränzle, Roderick Bloem, and Bettina Könighofer
    In 33th International Conference on Automated Planning and Scheduling ICAPS, 2023
  3. Provable Correct and Adaptive Simplex Architecture for Bounded-Liveness Properties
    Benedikt Maderbacher, Stefan Schupp, Ezio Bartocci, Roderick Bloem, Dejan Nickovic, and Bettina Könighofer
    In 29th International Symposium on Model Checking Software SPIN, 2023
  4. Formal XAI via Syntax-Guided Synthesis
    Katrine Bjørner, Samuel Judson, Filip Cano, Drew Goldman, Nicholas Shoemaker, Ruzica Piskac, and Bettina Könighofer
    In 1st International Conference on Bridging the Gap Between AI and Reality AISoLA, 2023
  5. Online shielding for reinforcement learning
    Bettina Könighofer, Julian Rudolf, Alexander Palmisano, Martin Tappler, and Roderick Bloem
    2023
  6. Tools at the Frontiers of Quantitative Verification - QComp 2023 Competition Report
    Roman Andriushchenko, Alexander Bork, Carlos E. Budde, Milan Ceska, Kush Grover, Ernst Moritz Hahn, Arnd Hartmanns, Bryant Israelsen, Nils Jansen, Joshua Jeppson, Sebastian Junges, Maximilian A. Köhl, Bettina Könighofer, Jan Kretı́nský, Tobias Meggendorfer, David Parker, Stefan Pranger, Tim Quatmann, Enno Ruijters, Landon Taylor, Matthias Volk, Maximilian Weininger, and Zhen Zhang
    In TOOLympics Challenge 2023 - Updates, Results, Successes of the Formal-Methods Competitions, 2023

2022

  1. Correct-by-Construction Runtime Enforcement in AI - A Survey
    Bettina Könighofer, Roderick Bloem, Rüdiger Ehlers, and Christian Pek
    In Principles of Systems Design - Essays Dedicated to Thomas A. Henzinger on the Occasion of His 60th Birthday, 2022
  2. Search-Based Testing of Reinforcement Learning
    Martin Tappler, Filip Cano Córdoba, Bernhard K. Aichernig, and Bettina Könighofer
    In 31st International Joint Conference on Artificial Intelligence IJCAI, 2022
  3. Automata Learning Meets Shielding
    Martin Tappler, Stefan Pranger, Bettina Könighofer, Edi Muskardin, Roderick Bloem, and Kim G. Larsen
    In 11th International Symposium on Leveraging Applications of Formal Methods ISoLA, 2022

2021

  1. Online Shielding for Stochastic Systems
    Bettina Könighofer, Julian Rudolf, Alexander Palmisano, Martin Tappler, and Roderick Bloem
    In 13th International Symposium on NASA Formal Methods NFM, 2021
  2. TEMPEST - Synthesis Tool for Reactive Systems and Shields in Probabilistic Environments
    Stefan Pranger, Bettina Könighofer, Lukas Posch, and Roderick Bloem
    In 19th International Symposium on Automated Technology for Verification and Analysis ATVA, 2021
  3. Adaptive Shielding under Uncertainty
    Stefan Pranger, Bettina Könighofer, Martin Tappler, Martin Deixelberger, Nils Jansen, and Roderick Bloem
    In 40th American Control Conference ACC, 2021

2020

  1. Shield Synthesis for Reinforcement Learning
    Bettina Könighofer, Florian Lorber, Nils Jansen, and Roderick Bloem
    In 9th International Symposium on Leveraging Applications of Formal Methods ISoLA, 2020
  2. Safe Reinforcement Learning Using Probabilistic Shields (Invited Paper)
    Nils Jansen, Bettina Könighofer, Sebastian Junges, Alex Serban, and Roderick Bloem
    In 31st International Conference on Concurrency Theory CONCUR, 2020

2019

  1. Run-Time Optimization for Learned Controllers Through Quantitative Games
    Guy Avni, Roderick Bloem, Krishnendu Chatterjee, Thomas A. Henzinger, Bettina Könighofer, and Stefan Pranger
    In 31st International Conference on Computer Aided Verification CAV, 2019
  2. Synthesis of Minimum-Cost Shields for Multi-agent Systems
    Suda Bharadwaj, Roderick Bloem, Rayna Dimitrova, Bettina Könighofer, and Ufuk Topcu
    In 38th American Control Conference ACC, 2019

2018

  1. Safe Reinforcement Learning via Shielding
    Mohammed Alshiekh, Roderick Bloem, Rüdiger Ehlers, Bettina Könighofer, Scott Niekum, and Ufuk Topcu
    In 32th Conference on Artificial Intelligence AAAI, 2018

2017

  1. Shield synthesis
    Bettina Könighofer, Mohammed Alshiekh, Roderick Bloem, Laura R. Humphrey, Robert Könighofer, Ufuk Topcu, and Chao Wang
    Formal Methods Syst. Des., 2017

2016

  1. Synthesis of Admissible Shields
    Laura R. Humphrey, Bettina Könighofer, Robert Könighofer, and Ufuk Topcu
    In 12th International Haifa Verification Conference on Hardware and Software: Verification and Testing HVC, 2016

2015

  1. Shield Synthesis: - Runtime Enforcement for Reactive Systems
    Roderick Bloem, Bettina Könighofer, Robert Könighofer, and Chao Wang
    In 21st International Conference on Tools and Algorithms for the Construction and Analysis of Systems TACAS, 2015