Martin Krutský

Martin is a Ph.D. student at the Intelligent Data Analysis lab, where he studies explainable AI with emphasis on neuro-symbolic and structured geometric models. Through his interest in explainability, he started exploring the interdisciplinary field of responsible AI, spanning from AI ethics to AI safety.
Martin cooperates with members of AIC through research projects and the Responsible AI discussion group.
Latest Projects
Research Results
Latest news

When the Hugging Face platform recently reported a security breach on its infrastructure, OpenAI soon claimed responsibility for the incident. According to the company, however, it was not a targeted attack. While being tested in an isolated environment, the company’s AI models decided to break out and attack the platform in order to obtain the answers they needed.

