Filip Cano Cordoba
Ing.PhD Candidate
Research
My research is focused on generating trustworthy artificial intelligence through the use of formal methods. I am particularly interested in accountability of AI systems and also in runtime verification and enforcement of safety-critical properties.Publications
Fairness Shields: Safeguarding against Biased Decision Makers
Cano Cordoba F., Henzinger T., Könighofer B., Kueffner K., Mallik K.
Proceedings of the AAAI Conference on Artificial Intelligence, AAAI Press, 15659-15668, (Proceedings of the AAAI Conference on Artificial Intelligence)
Analyzing Intentional Behavior in Autonomous Agents Under Uncertainty
Cano Cordoba F., Judson S., Antonopoulos T., Bjørner K., Shoemaker N., Shapiro S., Piskac R., Könighofer B.
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 32nd International Joint Conference on Artificial Intelligence, 372--381
Safety Shielding under Delayed Observation
Cano Cordoba F., Palmisano A., Fränzle M., Bloem R., Könighofer B.
Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), AAAI Press, 80-85, (Proceedings International Conference on Automated Planning and Scheduling, ICAPS)
Search-Based Testing of Reinforcement Learning
Tappler M., Cano Cordoba F., Aichernig B., Könighofer B.
Thirty-First International Joint Conference on Artificial Intelligence (IJCAI 2022), 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence, 503-510