Faculty
2025: Werner-von-Siemens-Fellow
2025: ERC Starting Grant
2024: GI Junior-Fellow
2024: Busy Beaver Award "Differential Privacy: Mathematical Foundations and Applications in Machine Learning“, Saarland University
Franziska Boenisch is a tenure-track faculty member at the CISPA Helmholtz Center for Information Security. At CISPA, she co-leads the SprintML Lab (Secure, Private, Robust, Interpretable, and Trustworthy Machine Learning), where her research focuses on advancing trustworthy machine learning. Prior to joining CISPA, she was a Postdoctoral Fellow at the Vector Institute for Artificial Intelligence, working under the supervision of Prof. Dr. Nicolas Papernot. She received her PhD from Freie Universität Berlin, where she also served as a research associate at the Fraunhofer Institute for Applied and Integrated Security (AISEC).
European Conference on Computer Vision (ECCV) Data Circuit Breaker: Identifying Training, Test, and Generated Data in Image Generative Models
The 19th European Conference on Computer Vision (ECCV), 2026 MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning
IH&MMSec '26: ACM Workshop on Information Hiding and Multimedia Security Watermark Degradation Across Model Iterations
Proceedings of the ACM Asia Conference on Computer and Communications Security ADAGE: Active Defenses Against GNN Extraction
International Conference on Machine Learning (ICML) Finding DoRI: Discovery of Retained Images in Diffusion Models
International Conference on Machine Learning (ICML) Concept Removal in Frontier Image Generative Models
International Conference on Learning Representations (ICLR) SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation
International Conference on Learning Representations (ICLR) Natural Identifiers for Privacy and Data Audits in Large Language Models
International Conference on Learning Representations (ICLR) Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
International Conference on Learning Representations (ICLR) Data Provenance for Image Auto-Regressive Generation