Mario Fritz

Mario Fritz is a faculty member at the CISPA Helmholtz Center for Information Security, an honorary professor at Saarland University, and a fellow of the European Laboratory for Learning and Intelligent Systems (ELLIS). Previously, he led a research group at the Max Planck Institute for Informatics (2011-2018) and conducted postdoctoral work at UC Berkeley. His research focuses on trustworthy artificial intelligence at the intersection of information security and machine learning, with recent projects including the EU-funded ELSA - European Lighthouse on Secure and Safe AI.

• Current roles: CISPA faculty (2018-present), Saarland University professor (2019-present)
• Past roles: Max Planck senior researcher (2011-2018), ICSI/UC Berkeley postdoc (2008-2010)
• Education: PhD from TU Darmstadt, computer science studies at FAU Erlangen-Nuremberg

His research spans AI security, privacy-preserving machine learning, computer vision, and deep generative models. Recent work includes LLM-based code deobfuscation, certified malware detectors, and membership inference attacks on DocVQA models.

He serves as Associate Editor for the journal IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and leads projects like Trustworthy Federated Data Analytics, PriSyn (synthetic health data with privacy), and ImageTox (automated toxicity detection). As of 2025, he has published over 100 scientific articles, including 80 in top venues like ICML, ICLR, and CVPR.