Franziska Boenisch

Franziska Boenisch

Tenure-Track Faculty
@ CISPA

Research focus:
Privacy-Preserving and Trustworthy ML.

Publications

This page provides an overview on my publications.

Author(s)YearTitle and PublicationLink
Jan Dubiński, Antoni Kowalczuk, Franziska Boenisch , Adam Dziedzic2025Privacy Attacks on Image AutoRegressive Models.
ICML		[Upcoming]
Xun Wang, Jing Xu, Franziska Boenisch , Michael Backes, Christopher A. Choquette-Choo, Adam Dziedzic2025Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs.
ICML		[Upcoming]
Bihe Zhao, Pratyush Maini, Franziska Boenisch , Adam Dziedzic2025Unlocking Post-hoc Dataset Inference with Synthetic Data.
ICML		[Upcoming]
Jan Dubiński, Antoni Kowalczuk, Franziska Boenisch , Adam Dziedzic2025CDI: Copyrighted Data Identification in Diffusion Models.
CVPR		here
Shahrzad Kiani, Nupur Kulkarni, Adam Dziedzic, Stark Draper, Franziska Boenisch2025Differentially Private Federated Learning with Time-Adaptive Privacy Spending.
ICLR		here
Łukasz Staniszewski, Bartosz Cywiński, Franziska Boenisch, Kamil Deja, Adam Dziedzic2025Precise Parameter Localization for Textual Generation in Diffusion Models.
ICLR		here
Wenhao Wang, Adam Dziedzic, Grace C. Kim, Michael Backes, Franziska Boenisch2025Captured by Captions: On Memorization and its Mitigation in CLIP Models.
ICLR		here
Dariush Wahdany, Matthew Jagielski, Adam Dziedzic, Franziska Boenisch2025Differentially Private Prototypes for Imbalanced Transfer Learning.
AAAI		here
Vincent Hanke, Tom Blanchard, Franziska Boenisch, Iyiola Emmanuel Olatunji, Michael Backes, Adam Dziedzic2024Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives.
NeurIPS		here
Wenhao Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch2024Localizing Memorization in SSL Vision Encoders.
NeurIPS		here
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch2024Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models.
NeurIPS		here
Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov, Jesse Cresswell, Franziska Boenisch , Nicolas Papernot2024Augment then Smooth: Reconciling Differential Privacy with Certified Robustness.
TMLR		here
Shahrzad Kiani, Franziska Boenisch, and Stark C Draper2024Controlled privacy leakage propagation throughout overlapping grouped learning.
IEEE Journal on Selected Areas in Information Theory		here
Wenhao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael Backes, Nicolas Papernot, and Franziska Boenisch2024Memorization in Self-Supervised Learning Improves Downstream Generalization.
ICLR		here
Anvith Thudi, Ilia Shumailov, Franziska Boenisch, and Nicolas Papernot2024From Differential Privacy to Bounds on Membership Inference: Less can be More.
TMLR		here
Haonan Duan, Adam Dziedzic, Mohammad Yaghini, Nicolas Papernot, and Franziska Boenisch2023On the Privacy Risk of In-context Learning.
ACL TrustNLP Workshop		here
Haonan Duan, Adam Dziedzic, Nicolas Papernot, and Franziska Boenisch2023Flocks of stochastic parrots: Differentially private prompt learning for large language models.
NeurIPS		here
Jan Dubiński, Stanisław Pawlak, Franziska Boenisch, Tomasz Trzcinski, and Adam Dziedzi2023Bucksforbuckets(b4b):Active defenses against stealing encoders
NeurIPS		here
Franziska Boenisch, Christopher Mühl, Adam Dziedzic, Roy Rinberg, Nicolas Papernot2023Have it your way: Individualized Privacy Assignment for DP-SGD
NeurIPS		here
Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov and Nicolas Papernot2023When the Curious Abandon Honesty: Federated Learning Is Not Private.
IEEE Euro S&P		here
Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov and Nicolas Papernot2023Is Federated Learning a Practical PET Yet?
IEEE Euro S&P		here
Franziska Boenisch, Christopher Mühl, Roy Rinberg, Jannis Ihrig, and Adam Dziedzic2023Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees.
23rd Privacy Enhancing Technologies Symposium (PoPETs ‘23)		here
Matteo Giomi, Franziska Boenisch, Christoph Wehmeyer, and Borbála Tasnádi2023A Unified Framework for Quantifying Privacy Risk in Synthetic Data.
23rd Privacy Enhancing Technologies Symposium (PoPETs ‘23)		here
Adam Dziedzic, Haonan Duan, Muhammad Ahmad Kaleem, Nikita Dhawan, Jonas Guan, Yannis Cattan, Franziska Boenisch, and Nicolas Papernot2022Dataset Inference for Self-Supervised Models.
NeurIPS		here
Karla Pizzi, Franziska Boenisch, Ugur Sahin, and Konstantin Böttinger2022Introducing Model Inversion Attacks on Automatic Speaker Recognition.
Proc. 2nd Symposium on Security and Privacy in Speech Communication		here
Tabea Kossen, Manuel Hirzel, Vince Madai, Franziska Boenisch, Anja Hennemuth, Kristian Hildebrand, Sebastian Pokutta, Kartikey Sharma, Adam Hilbert, Jan Sobesky, Ivana Galinovich, Ahmed Khalil, Jochen Fiebach, and Dietmar Frey.2022Towards sharing brain images: Differentially private TOF-MRA images with segmentation labels using generative adversarial networks.
Frontiers in Artificial Intelligence		here
Franziska Boenisch2021A Systematic Review on Model Watermarking for Neural Networks.
Frontiers in Big Data, 4(96).		here
Franziska Boenisch, Reinhard Munz, Marcel Tiepelt, Simon Hanisch, Christiane Kuhn, and Paul Francis2021Side-Channel Attacks on Query-Based Data Anonymization.
ACM CCS		here
Franziska Boenisch, Verena Battis, Nicolas Buchmann, and Maija Poikela2021“I Never Thought About Securing My Machine Learning Systems”: A Study of Security and Privacy Awareness of Machine Learning Practitioners
Mensch und Computer 2021, 520-546.		here
Sörries, Peter, Claudia Müller-Birn, Katrin Glinka, Franziska Boenisch, Marian Margraf, Sabine Sayegh-Jodehl, and Matthias Rose2021Privacy Needs Reflection: Conceptional Design Rationales for Privacy-Preserving Explanation User Interfaces.
Mensch und Computer 2021, Workshow-Proceedings.		here
Franziska Boenisch2021Privatsphäre und Maschinelles Lernen.
Datenschutz Datensicherheit 45, 448–452.		here
Franziska Boenisch, Philip Sperl, and Konstantin Böttinger2021Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning.
arXiv preprint arXiv:2105.07985		here
Franziska Boenisch, Benjamin Rosemann, Benjamin Wild, David Dormagen, Fernando Wario, and Tim Landgraf2018Tracking all members of a honey bee colony over their lifetime using learned models of correspondence.
Frontiers in Robotics and AI. 5(35).		here