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 ist Tenure-Track Faculty am CISPA Helmholtz-Zentrum für Informationssicherheit. Am CISPA ist sie Co-Leiterin des SprintML Lab (Secure, Private, Robust, Interpretable, and Trustworthy Machine Learning), in dem sie zur Weiterentwicklung von vertrauenswürdigem Machine Learning forscht. Zuvor war sie Postdoctoral Fellow am Vector Institute for Artificial Intelligence, betreut von Prof. Dr. Nicolas Papernot. Vor ihrem Wechsel an das Vector Institute war sie Doktorandin an der Freien Universität Berlin sowie wissenschaftliche Mitarbeiterin am Fraunhofer-Institut für Angewandte und Integrierte Sicherheit (AISEC).
National Conference of the American Association for Artificial Intelligence (AAAI) On Stealing Graph Neural Network Models
Association for the Advancement of Artificial Intelligence (AAAI) Demystifying Foreground-Background Memorization in Diffusion Models
AAAI 2026 Workshop on AI Governance Frequency-Domain Model Fingerprinting for Image Autoregressive Models
ICLR 2026 Workshop: Principled Design for Trustworthy AI
International Conference on Learning Representations (ICLR) Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
Conference on Neural Information Processing Systems (NeurIPS) Exploring the limits of strong membership inference attacks on large language models
Conference on Neural Information Processing Systems (NeurIPS) Memorization in Graph Neural Networks
National Conference of the American Association for Artificial Intelligence (AAAI) Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
Conference on Neural Information Processing Systems (NeurIPS) BitMark: Watermarking Bitwise Autoregressive Image Generative Models
Naval Research Logistics Personalized Differential Privacy for Ridge Regression Under Output Perturbation