Mario Fritz

Prof. Dr. Mario Fritz is a leading academic at the CISPA Helmholtz Center for Information Security and Saarland University, with a focus on Trustworthy Information Processing. His work sits at the intersection of AI, Machine Learning, Security, and Privacy, addressing challenges in foundation models, health data, and adversarial robustness.

• Key Projects: ELLIOT (Multi-Modal Foundation Models), ELSA (Secure AI), PriSyn (Synthetic Health Data), AIgency (Generative AI in Cybersecurity), HMSP (Medical Security)
• Research Themes: AI/ML security, privacy-preserving techniques, causal modeling, healthcare applications, and ethical AI
• Recent Publications: Focus on LLM sampling, causal inference, model stealing, and privacy-aware document analysis
• Collaborations: European Laboratory for Learning and Intelligent Systems (ELLIS), BMBF-funded initiatives, GHGA (Human Genome Archive)

Academic Leadership: As a Professor, he coordinates large-scale EU projects and mentors emerging researchers in AI ethics and security.