Faculty
Mario Fritz is a faculty 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).
Until 2018, he led a research group at the Max Planck Institute for Computer Science.
Previously, he was a PostDoc at the International Computer Science Institute (ICSI) and UC Berkeley after receiving his PhD from TU Darmstadt and studying computer science at FAU Erlangen-Nuremberg.
He is currently coordinating and leading the EU funded network of excellence "ELSA - European Lighthouse on Secure and Safe AI", among other projects.
His research focuses on trustworthy artificial intelligence, especially at the intersection of information security and machine learning.
Privacy Enhancing Technologies Symposium (PETS)
FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations
International Conference on Machine Learning (ICML)
Stealthy Imitation: Reward-guided Environment-free Policy Stealing
International Conference on Machine Learning (ICML)
MultiMax: Sparse and Multi-Modal Attention Learning
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)
SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models
IEEE Transactions on Pattern Analysis and Machine Intelligence B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers.
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)
PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
International Conference on Machine Learning (ICML)
Stealthy Imitation: Reward-guided Environment-free Policy Stealing.
Transactions on Machine Learning Research (TMLR) A Unified View of Differentially Private Deep Generative Modeling.
German Conference on Pattern Recognition (GCPR)
MargCTGAN: A “Marginally” Better CTGAN for the Low Sample Regime
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models