Helge Spieker

Helge Spieker

Software Testing,Trustworthy AI & ML, Constraint Programming

Welcome to Helge Spieker’s Website

Hi, I’m a research scientist at Simula Research Laboratory in Oslo, Norway. My current research topics are software testing of complex systems, like those involving AI/ML-based components, and the application of symbolic AI and ML to software testing problems.

I completed my PhD (2020) at University of Oslo and Simula within the Certus Centre for Software Validation and Verification (Certus SFI) under the supervision of Arnaud Gotlieb, Magne Jørgensen and Morten Mossige.

Research Interests

My research focuses on enhancing software reliability and trustworthiness at the intersection of Software Engineering (SE), particularly software testing, and Artificial Intelligence (AI)/Machine Learning (ML). Recognizing the increasing complexity of modern software, I develop effective and efficient testing methods crucial for creating solid and reliable systems. I focus specifically on the testing of complex systems, especially those with AI/ML components, and the application of AI/ML techniques to software engineering tasks.

Main Publications

An up-to-date list of all publications can be found on dblp or Google Scholar.

  • [Conference] Gross, Dennis and Helge Spieker (2025). “PCTL Model Checking for Temporal RL Policy Safety Explanations”. In: 40th ACM/SIGAPP Symposium On Applied Computing (SAC).
  • [Conference] Gross, Dennis and Helge Spieker (2025). “Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies”. In: 17th International Conference on Agents and Artificial Intelligence (ICAART). doi: 10.5220/0013255500003890. Preprint
  • [Journal] Mazouni, Quentin, Arnaud Gotlieb, Spieker, Helge, Mathieu Acher, and Benoit Combemale (2025). “Mutation- Guided Metamorphic Testing of Optimality in AI Planning”. In: Software Testing, Verification and Reliability. doi: 10.1002/stvr.1898.
  • [Journal] Linløkken, M.-S., F. Meyer, C. Högström, P. Jølstad, Spieker, Helge, S. Guillaume, S. Hoholm, F. Wolfsperger, and M. Gilgien (2025). “Equivalent Fall Height and Aerial Maneuver Difficulty Both Influence Landing Stability on World Cup Slopestyle Rollover Jumps For Skiers and Snowboarders”. In: Scandinavian Journal of Medicine & Science in Sports 35.4, e70053. doi: https://doi.org/10.1111/sms.70053.
  • [Conference] Mazouni, Quentin, Spieker, Helge, Arnaud Gotlieb, and Mathieu Acher (2024). “Policy Testing with MDPFuzz (Replicability Study)”. In: International Symposium on Software Testing and Analysis (ISSTA). doi: 10.1145/3650212.3680382. Preprint
  • [Conference] Spieker, Helge, Nassim Belmecheri, Arnaud Gotlieb, and Nadjib Lazaar (2024). “Evaluating Human Trajectory Prediction with Metamorphic Testing”. In: 9th ACM International Workshop on Metamorphic Testing (MET). doi: 10.1145/3679006.3685071. Preprint.
  • [Conference] Gross, Dennis and Helge Spieker (2024). “Enhancing RL Safety with Counterfactual LLM Reasoning”. In: 36th International Conference on Testing Software and Systems (ICTSS). Preprint
  • [Conference] Gross, Dennis and Helge Spieker (2024). “Safety-Oriented Pruning and Interpretation of Reinforcement Learning Policies”. In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). Preprint
  • [Conference] Mazouni, Quentin, Helge Spieker, Arnaud Gotlieb, and Mathieu Acher (2024). “Testing for Fault Diversity in Reinforcement Learning”. In: 5th ACM/IEEE International Conference on Automation of Software Test (AST). ACM, pp. 136–146. doi: 10.1145/3644032.3644458. Preprint
  • [Conference] Gross, Dennis and Helge Spieker (2024). “Probabilistic Model Checking of Stochastic Reinforcement Learning Policies”. In: 16th International Conference on Agents and Artificial Intelligence (ICAART). doi: 10.5220/0012357700003636. Preprint
  • [Conference] Gross, Dennis, Helge Spieker, Arnaud Gotlieb, and Ricardo Knoblauch (2024). “Enhancing Manufacturing Quality Prediction Models Through the Integration of Explainability Methods”. In: 16th International Conference on Agents and Artificial Intelligence (ICAART). doi: 10.5220/0012417800003636. Preprint
  • [Journal] Belmecheri, Nassim, Arnaud Gotlieb, Nadjib Lazaar, and Helge Spieker (2024). “Towards Trustworthy Automated Driving through Qualitative Scene Understanding and Explanations”. In: SAE International Journal of Connected and Automated Vehicles 8. doi: 10.4271/12-08-01-0003. Preprint
  • [Journal] Belaid, M. B., Belmecheri, N., Gotlieb, A., Lazaar, N., Spieker, H. (2024). Query-driven Qualitative Constraint Acquisition. Journal of Artificial Intelligence Research (JAIR). DOI: 10.1613/jair.1.14752
  • [Journal] Lesoil, L., Spieker, H., Gotlieb, A., Acher, M., Temple, P., Blouin, A., Jezequel, J. (2024). Learning Input-aware Performance Models of Configurable Systems: An Empirical Evaluation. Journal of Systems and Software (JSS). DOI: 10.1016/j.jss.2023.111883 Preprint
  • [Conference] Belmecheri, N., Gotlieb, A., Lazaar, N., Spieker, H. (2024). Trustworthy Automated Driving through Qualitative Scene Understanding and Explanations. Transport Research Arena (TRA). PDF
  • [Conference] Gross, D., Knoblauch, R., Spieker, H., Gotlieb, A. (2024). Enhancing Manufacturing Quality Prediction Models through the Integration of Explainability Methods. International Conference on Agents and Artificial Intelligence (ICAART). DOI: 10.5220/0012417800003636
  • [Conference] Gross, D., Spieker, H. (2024). Probabilistic Model Checking of Stochastic Reinforcement Learning Policies. International Conference on Agents and Artificial Intelligence (ICAART). DOI: 10.5220/0012357700003636
  • [Journal] Bernabé, P., Gotlieb, A., Legeard, B., Marijan, D., Sem-Jacobsen, F.O., Spieker, H. (2023). Detecting Intentional AIS Shutdown in Open Sea Maritime Surveillance Using Self-Supervised Deep Learning. IEEE Transactions on Intelligent Transportation Systems. DOI: 10.1109/TITS.2023.3322690
  • [Conference] Gotlieb, A., Mossige, M., Spieker, H. (2023). Constraint-guided Test Execution Scheduling: An Experience Report at ABB Robotics. International Conference on Computer Safety, Reliability and Security (SAFECOMP). DOI: 10.1007/978-3-031-40923-3_6 arXiv
  • [Conference] Mazouni, Q., Spieker, H., Gotlieb, A., Acher, M. (2023). A Review of Validation and Verification of Neural Network-based Policies for Sequential Decision Making. Rencontres des Jeunes Chercheurs en Intelligence Artificielle (RJCIA). PDF
  • [Journal] Herbold, S., …, Spieker, H., et al. (2022). A Fine-grained Data Set and Analysis of Tangling in Bug Fixing Commits. Empirical Software Engineering (EMSE). DOI: 10.1007/s10664-021-10083-5 arXiv
  • [Conference] Ahuja, M.K., Sahil, S., Spieker, H. (2022). FoCA: Failure-oriented Class Augmentation for Robust Image Classification. IEEE International Conference on Tools with Artificial Intelligence (ICTAI). DOI: 10.1109/ICTAI56018.2022.00144
  • [Workshop] Ahuja, M.K., Gotlieb, A., Spieker, H. (2022). Testing Deep Learning Models: A First Comparative Study of Multiple Testing Techniques. Artificial Intelligence in Software Testing @ ICST 2022. DOI: 10.1109/ICSTW55395.2022.00035 arXiv
  • [Conference] Belaid, M. B., Belmecheri, N., Gotlieb, A., Lazaar, N., Spieker, H. (2022). GEQCA: Generic Qualitative Constraint Acquisition. AAAI. DOI: 10.1609/aaai.v36i4.20282
  • [Journal] Spieker, H., Gotlieb, A. (2021). Predictive Machine Learning of Objective Boundaries for Solving COPs. AI. Vol. 2, No. 4. MDPI. DOI: 10.3390/ai2040033 arXiv
  • [Book Chapter] Gotlieb, A., Marijan, D., Spieker, H. (2021). Testing Industrial Robotic Systems: A New Battlefield!. In: Cavalcanti, A., Dongol, B., Hierons, R., Timmis, J., Woodcock, J. (eds) Software Engineering for Robotics. Springer, Cham. DOI: 10.1007/978-3-030-66494-7_4
  • [Conference] Spieker, H. (2021). Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-Interaction. International Joint Conference on Neural Networks (IJCNN). arXiv
  • [Conference] Ahuja, M. K., Belaid, M. B., Bernabé, P., Gotlieb, A., Marijan, D., Sharif, A., Spieker, H. (2021). In Proceedings of the 31st European Safety and Reliability Conference (ESREL). ESREL, 2021.
  • [Journal] Gotlieb, A., Marijan, D., Spieker, H. (2020). ITE: A Lightweight Implementation of Stratified Reasoning for Constructive Logical Operators. International Journal on Artificial Intelligence Tools. Vol. 29, No. 03n04. DOI: 10.1142/S0218213020600064 arXiv
  • [Conference] Spieker, H., Gotlieb, A. (2020). Learning Objective Boundaries for Constraint Optimization Problems. Machine Learning, Optimization, and Data Science. LOD 2020. Lecture Notes in Computer Science, vol 12566. DOI: 10.1007/978-3-030-64580-9_33 arXiv
  • [Workshop] Ahuja, M.K., Belaid, M.B., Bernabe, P., Collet, M., Gotlieb, A., Lal, C., Marijan, D., Sen, S., Sharif, A., Spieker, H. (2020). Opening the Software Engineering Toolbox for the Assessment of Trustworthy AI. In 1st International Workshop on New Foundations for Human-Centered AI @ ECAI 2020. arXiv PDF
  • [Journal] Spieker, H., Gotlieb, A. (2020). Adaptive Metamorphic Testing with Contextual Bandits. Journal of Systems and Software. DOI: 10.1016/j.jss.2020.110574 arXiv
  • [Conference] Spieker, H., Gotlieb, A., & Mossige, M. (2019). Rotational Diversity in Multi-Cycle Assignment Problems. In Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), pp. 7724-7731. DOI: 10.1609/aaai.v33i01.33017724 PDF arXiv
  • [Conference] Gotlieb, A., Marijan, D., & Spieker, H. (2018). Stratified Constructive Disjunction and Negation in Constraint Programming. In International Conference on Tools with Artificial Intelligence. DOI: 10.1109/ICTAI.2018.00026 PDF arXiv
  • [Workshop] Spieker, H., & Gotlieb, A. (2018). Towards Hybrid Constraint Solving with Reinforcement Learning and Constraint-Based Local Search. In Data Science meets Optimization Workshop at Federated Artificial Intelligence Meeting. PDF
  • [Conference] Mossige, M., Gotlieb, A., Spieker, H., Meling, H., & Carlsson, M. (2017). Time-Aware Test Case Execution Scheduling for Cyber-Physical Systems. In Proceedings of the 23rd International Conference on Principles and Practice of Constraint Programming (Vol. 10416, pp. 386–404). DOI: 10.1007/978-3-319-66158-2_25 PDF arXiv
  • [Conference] Spieker, H., Gotlieb, A., Marijan, D., & Mossige, M. (2017). Reinforcement Learning for Automatic Test Case Prioritization and Selection in Continuous Integration. In Proceedings of 26th International Symposium on Software Testing and Analysis (ISSTA’17) (pp. 12–22). DOI: 10.1145/3092703.3092709 PDF arXiv
  • [Journal] Spieker, H., Hagg, A., Gaier, A., Meilinger, S., & Asteroth, A. (2017). Multi-stage evolution of single- and multi-objective MCLP: Successive placement of charging stations. Soft Computing (Vol. 21, Issue 17, pp. 4859-4872). DOI: 10.1007/s00500-016-2374-9 PDF
  • [Conference] Spieker, H., Hagg, A., Asteroth, A., Meilinger, S., Jacobs, V., & Oslislo, A. (2015). Successive evolution of charging station placement. In 2015 International Symposium on Innovations in Intelligent SysTems and Applications (INISTA). DOI: 10.1109/INISTA.2015.7276733 PDF

Activities

I am proud to be or have been a program committee member and reviewer of

IJCAI 2025, ICML 2025, AIST @ ICST 2025, ECAI 2024, ICLR 2024, ICML 2024, AIST @ ICST 2023, ICLR 2023, ICML 2023, IJCAI 2023, ISSTA 2023 - Artifact Evaluation, LOPSTR 2023, TRA 2024, AAAI 2022, AIST @ ICST 2022, CP 2022, ICLR 2022, IJCAI-ECAI 2022, NeurIPS 2022, SEA4DQ 2022, AAAI 2021, ICLR 2021, ICML 2021, NeurIPS 2021, QRS 2021, SEA4DQ 2021, SER&IP @ ICSE 2021, IEEE AI Testing 2021, AAAI 2020, ICML 2020, NeurIPS 2020, QRS 2020, SER&IP @ ICSE 2020, IEEE AI Testing 2020, IEEE AI Testing 2019.

I was a member of the associate editorial board of Applied AI Letters (2021-2024).

I have been or currently am a reviewer for these journals: IEEE TSE, IEEE TRel, TOSEM, STVR, JSS, IST, EMSE, CAOR, AMAI.

It was a great pleasure to have been a co-organizer of the NordConsNet Workshop 2019.

If you want to check out what other great people (and especially bachelor and master students in Germany) are doing, check out the: German InformatiCup. I’m helping out in the jury, but the impressive results stem from the student groups!

Contact

Please feel free to contact me by using the contact information in the sidebar. You can also find more information on my Simula Homepage.