Mateusz Kowalczyk

Research interests: AI Security/Safety, Adversarial Machine Learning, Multimodal AI
Mateusz has been affiliated with NASK since 2021. He focuses on the security of machine learning models, particularly in the area of Adversarial Machine Learning. His professional interests include analyzing the robustness of artificial intelligence models against intentional manipulations and attacks, as well as developing methods to enhance their reliability.
In 2024, he began his doctoral studies at the TIB PAN Doctoral School, where he is pursuing a PhD titled “Robustness of machine learning models considering adversarial conditions.” His research focuses on the robustness of multimodal models against adversarial attacks, with particular emphasis on cross-modal adversarial threats.
Selected Publications
Articles
Mateusz Kowalczyk, Karolina Seweryn, Joanna Kołodziej, Mateusz Krzysztoń, "Adversarial Robustness of Multimodal Machine Learning Models", Proceedings of the 39th ECMS International Conference on Modelling and Simulation, ECMS 2025, , 248-254.