Mario Fritz

Prof. Dr. Mario Fritz is a Professor at Saarland University and faculty member at CISPA Helmholtz Center for Information Security. He serves as a Fellow at the European Laboratory for Learning and Intelligent Systems (ELLIS). His research focuses on Trustworthy Information Processing at the intersection of AI & Machine Learning with Security & Privacy.

Mario Fritz leads numerous significant research initiatives including the European Large Open Multi-Modal Foundation Models for Robust Generalization (ELLIOT), European Lighthouse on Secure and Safe AI (ELSA), and multiple projects on privacy-preserving AI applications in healthcare. His work spans security and privacy aspects of large language models, foundation models, and medical AI applications. He has established himself as a leading researcher in trustworthy AI through his extensive publication record and leadership in major collaborative projects.

His recent research (2025 publications) demonstrates a strong focus on the security and safety challenges of large language models, including model stealing attacks, causal reasoning capabilities, sampling methods, and privacy risks. His work bridges theoretical foundations with practical applications across multiple domains, particularly in healthcare and cybersecurity.

Mario Fritz actively mentors PhD students and Post-Docs, seeking new researchers to join his group. He has been involved in numerous grants and collaborative projects, including those funded by BMBF and the Helmholtz Association, demonstrating his ability to secure substantial research funding and lead large interdisciplinary teams.