Franziska Boenisch

88 papers A* 20A 3B 1Misc 1Journal 59Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images. AAAI Aditya Kumar, Tom Blanchard, Adam Dziedzic, Franziska Boenisch
2026	J	`jnl`	Conditioned Activation Transport for T2I Safety Steering. CoRR Maciej Chrabaszcz, Aleksander Szymczyk, Jan Dubinski, Tomasz Trzcinski, Franziska Boenisch, Adam Dziedzic
2026	J	`jnl`	Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning. CoRR Dariush Wahdany, Matthew Jagielski, Adam Dziedzic, Franziska Boenisch
2026	A*	`conf`	Demystifying Foreground-Background Memorization in Diffusion Models. AAAI Jimmy Z. Di, Yiwei Lu, Yaoliang Yu, Gautam Kamath, Adam Dziedzic, Franziska Boenisch
2026	A*	`conf`	On Stealing Graph Neural Network Models. AAAI Marcin Podhajski, Jan Dubinski, Franziska Boenisch, Adam Dziedzic, Agnieszka Pregowska, Tomasz Pawel Michalak
2026	J	`jnl`	SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation. CoRR Jan Kociszewski, Hubert Jastrzebski, Tymoteusz Stepkowski, Filip Manijak, Krzysztof Rojek, Franziska Boenisch, Adam Dziedzic
2025	J	`jnl`	A self-portrayal of GI Junior Fellow Franziska Boenisch: trustworthy machine learning for individuals. it Inf. Technol. Franziska Boenisch
2025	J	`jnl`	Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs). CoRR Iyiola E. Olatunji, Franziska Boenisch, Jing Xu, Adam Dziedzic
2025	J	`jnl`	Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images. CoRR Aditya Kumar, Tom Blanchard, Adam Dziedzic, Franziska Boenisch
2025	J	`jnl`	BitMark for Infinity: Watermarking Bitwise Autoregressive Image Generative Models. CoRR Louis Kerner, Michel Meintz, Bihe Zhao, Franziska Boenisch, Adam Dziedzic
2025	A*	`conf`	CDI: Copyrighted Data Identification in Diffusion Models. CVPR Jan Dubinski, Antoni Kowalczuk, Franziska Boenisch, Adam Dziedzic
2025	A*	`conf`	Captured by Captions: On Memorization and its Mitigation in CLIP Models. ICLR Wenhao Wang, Adam Dziedzic, Grace C. Kim, Michael Backes, Franziska Boenisch
2025	J	`jnl`	Captured by Captions: On Memorization and its Mitigation in CLIP Models. CoRR Wenhao Wang, Adam Dziedzic, Grace C. Kim, Michael Backes, Franziska Boenisch
2025	J	`jnl`	Controlled privacy leakage propagation throughout overlapping grouped learning. CoRR Shahrzad Kiani, Franziska Boenisch, Stark C. Draper
2025	J	`jnl`	Demystifying Foreground-Background Memorization in Diffusion Models. CoRR Jimmy Z. Di, Yiwei Lu, Yaoliang Yu, Gautam Kamath, Adam Dziedzic, Franziska Boenisch
2025	J	`jnl`	Differentially Private Federated Learning With Time-Adaptive Privacy Spending. CoRR Shahrzad Kiani, Nupur Kulkarni, Adam Dziedzic, Stark C. Draper, Franziska Boenisch
2025	A*	`conf`	Differentially Private Federated Learning with Time-Adaptive Privacy Spending. ICLR Shahrzad Kiani, Nupur Kulkarni, Adam Dziedzic, Stark C. Draper, Franziska Boenisch
2025	A*	`conf`	Differentially Private Prototypes for Imbalanced Transfer Learning. AAAI Dariush Wahdany, Matthew Jagielski, Adam Dziedzic, Franziska Boenisch
2025	A*	`conf`	Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs. ICML Xun Wang, Jing Xu, Franziska Boenisch, Michael Backes, Christopher A. Choquette-Choo, Adam Dziedzic
2025	J	`jnl`	Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs. CoRR Xun Wang, Jing Xu, Franziska Boenisch, Michael Backes, Christopher A. Choquette-Choo, Adam Dziedzic
2025	J	`jnl`	Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed. CoRR Antoni Kowalczuk, Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch
2025	J	`jnl`	Implementing Adaptations for Vision AutoRegressive Model. CoRR Kaif Shaikh, Franziska Boenisch, Adam Dziedzic
2025	J	`jnl`	Localizing and Mitigating Memorization in Image Autoregressive Models. CoRR Aditya Kasliwal, Franziska Boenisch, Adam Dziedzic
2025	J	`jnl`	MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation. Trans. Mach. Learn. Res. Yihan Wang, Yiwei Lu, Guojun Zhang, Franziska Boenisch, Adam Dziedzic, Yaoliang Yu, Xiao-Shan Gao
2025	J	`jnl`	Memorization in Graph Neural Networks. CoRR Adarsh Jamadandi, Jing Xu, Adam Dziedzic, Franziska Boenisch
2025	J	`jnl`	On Stealing Graph Neural Network Models. CoRR Marcin Podhajski, Jan Dubinski, Franziska Boenisch, Adam Dziedzic, Agnieszka Pregowska, Tomasz P. Michalak
2025	A*	`conf`	Precise Parameter Localization for Textual Generation in Diffusion Models. ICLR Lukasz Staniszewski, Bartosz Cywinski, Franziska Boenisch, Kamil Deja, Adam Dziedzic
2025	J	`jnl`	Precise Parameter Localization for Textual Generation in Diffusion Models. CoRR Lukasz Staniszewski, Bartosz Cywinski, Franziska Boenisch, Kamil Deja, Adam Dziedzic
2025	A*	`conf`	Privacy Attacks on Image AutoRegressive Models. ICML Antoni Kowalczuk, Jan Dubinski, Franziska Boenisch, Adam Dziedzic
2025	J	`jnl`	Privacy Attacks on Image AutoRegressive Models. CoRR Antoni Kowalczuk, Jan Dubinski, Franziska Boenisch, Adam Dziedzic
2025	J	`jnl`	Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models. CoRR Michel Meintz, Jan Dubinski, Franziska Boenisch, Adam Dziedzic
2025	J	`jnl`	Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models. CoRR Jamie Hayes, Ilia Shumailov, Christopher A. Choquette-Choo, Matthew Jagielski, Georgios Kaissis, Katherine Lee, Milad Nasr, Sahra Ghalebikesabi, Niloofar Mireshghallah, Meenatchi Sundaram Mutu Selva Annamalai, Igor Shilov, Matthieu Meeus, Yves-Alexandre de Montjoye, Franziska Boenisch, Adam Dziedzic, A. Feder Cooper
2025	A*	`conf`	Unlocking Post-hoc Dataset Inference with Synthetic Data. ICML Bihe Zhao, Pratyush Maini, Franziska Boenisch, Adam Dziedzic
2025	J	`jnl`	Unlocking Post-hoc Dataset Inference with Synthetic Data. CoRR Bihe Zhao, Pratyush Maini, Franziska Boenisch, Adam Dziedzic
2024	J	`jnl`	Alignment Calibration: Machine Unlearning for Contrastive Learning under Auditing. CoRR Yihan Wang, Yiwei Lu, Guojun Zhang, Franziska Boenisch, Adam Dziedzic, Yaoliang Yu, Xiao-Shan Gao
2024	J	`jnl`	Augment then Smooth: Reconciling Differential Privacy with Certified Robustness. Trans. Mach. Learn. Res. Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov, Jesse C. Cresswell, Franziska Boenisch, Nicolas Papernot
2024	J	`jnl`	Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks. CoRR Antoni Kowalczuk, Jan Dubinski, Atiyeh Ashari Ghomi, Yi Sui, George Stein, Jiapeng Wu, Jesse C. Cresswell, Franziska Boenisch, Adam Dziedzic
2024	J	`jnl`	Beyond the Mean: Differentially Private Prototypes for Private Transfer Learning. CoRR Dariush Wahdany, Matthew Jagielski, Adam Dziedzic, Franziska Boenisch
2024	J	`jnl`	CDI: Copyrighted Data Identification in Diffusion Models. CoRR Jan Dubinski, Antoni Kowalczuk, Franziska Boenisch, Adam Dziedzic
2024	J	`jnl`	Controlled Privacy Leakage Propagation Throughout Overlapping Grouped Learning. IEEE J. Sel. Areas Inf. Theory Shahrzad Kiani, Franziska Boenisch, Stark C. Draper
2024	B	`conf`	Controlled privacy leakage propagation throughout differential private overlapping grouped learning. ISIT Shahrzad Kiani, Franziska Boenisch, Stark C. Draper
2024	A	`conf`	Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks. ECAI Marcin Podhajski, Jan Dubinski, Franziska Boenisch, Adam Dziedzic, Agnieszka Pregowska, Tomasz P. Michalak
2024	J	`jnl`	Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks. CoRR Marcin Podhajski, Jan Dubinski, Franziska Boenisch, Adam Dziedzic, Agnieszka Pregowska, Tomasz P. Michalak
2024	A*	`conf`	Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models. NeurIPS Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch
2024	J	`jnl`	Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models. CoRR Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch
2024	J	`jnl`	From Differential Privacy to Bounds on Membership Inference: Less can be More. Trans. Mach. Learn. Res. Anvith Thudi, Ilia Shumailov, Franziska Boenisch, Nicolas Papernot
2024	A*	`conf`	Localizing Memorization in SSL Vision Encoders. NeurIPS Wenhao Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch
2024	J	`jnl`	Localizing Memorization in SSL Vision Encoders. CoRR Wenhao Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch
2024	A*	`conf`	Memorization in Self-Supervised Learning Improves Downstream Generalization. ICLR Wenhao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael Backes, Nicolas Papernot, Franziska Boenisch
2024	J	`jnl`	Memorization in Self-Supervised Learning Improves Downstream Generalization. CoRR Wenhao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael Backes, Nicolas Papernot, Franziska Boenisch
2024	J	`jnl`	On the Privacy Risk of In-context Learning. CoRR Haonan Duan, Adam Dziedzic, Mohammad Yaghini, Nicolas Papernot, Franziska Boenisch
2024	A*	`conf`	Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives. NeurIPS Vincent Hanke, Tom Blanchard, Franziska Boenisch, Iyiola E. Olatunji, Michael Backes, Adam Dziedzic
2024	J	`jnl`	Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives. CoRR Vincent Hanke, Tom Blanchard, Franziska Boenisch, Iyiola E. Olatunji, Michael Backes, Adam Dziedzic
2024	J	`jnl`	Personalized Differential Privacy for Ridge Regression. CoRR Krishna Acharya, Franziska Boenisch, Rakshit Naidu, Juba Ziani
2024	J	`jnl`	Regulation Games for Trustworthy Machine Learning. CoRR Mohammad Yaghini, Patty Liu, Franziska Boenisch, Nicolas Papernot
2023	J	`jnl`	A Unified Framework for Quantifying Privacy Risk in Synthetic Data. Proc. Priv. Enhancing Technol. Matteo Giomi, Franziska Boenisch, Christoph Wehmeyer, Borbála Tasnádi
2023	J	`jnl`	Augment then Smooth: Reconciling Differential Privacy with Certified Robustness. CoRR Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov, Jesse C. Cresswell, Franziska Boenisch, Nicolas Papernot
2023	A*	`conf`	Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders. NeurIPS Jan Dubinski, Stanislaw Pawlak, Franziska Boenisch, Tomasz Trzcinski, Adam Dziedzic
2023	J	`jnl`	Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders. CoRR Jan Dubinski, Stanislaw Pawlak, Franziska Boenisch, Tomasz Trzcinski, Adam Dziedzic
2023	A*	`conf`	Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models. NeurIPS Haonan Duan, Adam Dziedzic, Nicolas Papernot, Franziska Boenisch
2023	J	`jnl`	Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models. CoRR Haonan Duan, Adam Dziedzic, Nicolas Papernot, Franziska Boenisch
2023	A*	`conf`	Have it your way: Individualized Privacy Assignment for DP-SGD. NeurIPS Franziska Boenisch, Christopher Mühl, Adam Dziedzic, Roy Rinberg, Nicolas Papernot
2023	J	`jnl`	Have it your way: Individualized Privacy Assignment for DP-SGD. CoRR Franziska Boenisch, Christopher Mühl, Adam Dziedzic, Roy Rinberg, Nicolas Papernot
2023	J	`jnl`	Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees. Proc. Priv. Enhancing Technol. Franziska Boenisch, Christopher Mühl, Roy Rinberg, Jannis Ihrig, Adam Dziedzic
2023	J	`jnl`	Introducing Model Inversion Attacks on Automatic Speaker Recognition. CoRR Karla Pizzi, Franziska Boenisch, Ugur Sahin, Konstantin Böttinger
2023	J	`jnl`	Is Federated Learning a Practical PET Yet? CoRR Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
2023	J	`jnl`	Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility. CoRR Mohammad Yaghini, Patty Liu, Franziska Boenisch, Nicolas Papernot
2023	A	`conf`	Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation. EuroS&P Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
2023	A	`conf`	When the Curious Abandon Honesty: Federated Learning Is Not Private. EuroS&P Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
2022	J	`jnl`	A Unified Framework for Quantifying Privacy Risk in Synthetic Data. CoRR Matteo Giomi, Franziska Boenisch, Christoph Wehmeyer, Borbála Tasnádi
2022	J	`jnl`	Bounding Membership Inference. CoRR Anvith Thudi, Ilia Shumailov, Franziska Boenisch, Nicolas Papernot
2022	A*	`conf`	Dataset Inference for Self-Supervised Models. NeurIPS Adam Dziedzic, Haonan Duan, Muhammad Ahmad Kaleem, Nikita Dhawan, Jonas Guan, Yannis Cattan, Franziska Boenisch, Nicolas Papernot
2022	J	`jnl`	Dataset Inference for Self-Supervised Models. CoRR Adam Dziedzic, Haonan Duan, Muhammad Ahmad Kaleem, Nikita Dhawan, Jonas Guan, Yannis Cattan, Franziska Boenisch, Nicolas Papernot
2022	J	`jnl`	Personalized PATE: Differential Privacy for Machine Learning with Individual Privacy Guarantees. CoRR Christopher Mühl, Franziska Boenisch
2022	—	`—`	Secure and Private Machine Learning. Franziska Boenisch
2022	—	`conf`	The Influence of Training Parameters on Neural Networks' Vulnerability to Membership Inference Attacks. GI-Jahrestagung Oussama Bouanani, Franziska Boenisch
2022	J	`jnl`	Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks. Frontiers Artif. Intell. Tabea Kossen, Manuel A. Hirzel, Vince I. Madai, Franziska Boenisch, Anja Hennemuth, Kristian Hildebrand, Sebastian Pokutta, Kartikey Sharma, Adam Hilbert, Jan Sobesky, Ivana Galinovic, Ahmed A. Khalil, Jochen B. Fiebach, Dietmar Frey
2021	Misc	`conf`	"I Never Thought About Securing My Machine Learning Systems": A Study of Security and Privacy Awareness of Machine Learning Practitioners. MuC Franziska Boenisch, Verena Battis, Nicolas Buchmann, Maija Poikela
2021	J	`jnl`	A Systematic Review on Model Watermarking for Neural Networks. Frontiers Big Data Franziska Boenisch
2021	J	`jnl`	Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning. CoRR Franziska Boenisch, Philip Sperl, Konstantin Böttinger
2021	—	`conf`	Privacy Needs Reflection: Conceptional Design Rationales for Privacy-Preserving Explanation User Interfaces. MuC (Workshopband) Peter Sörries, Claudia Müller-Birn, Katrin Glinka, Franziska Boenisch, Marian Margraf, Sabine Sayegh-Jodehl, Matthias Rose
2021	J	`jnl`	Privatsphäre und Maschinelles Lernen. Datenschutz und Datensicherheit Franziska Boenisch
2021	A*	`conf`	Side-Channel Attacks on Query-Based Data Anonymization. CCS Franziska Boenisch, Reinhard Munz, Marcel Tiepelt, Simon Hanisch, Christiane Kuhn, Paul Francis
2021	J	`jnl`	When the Curious Abandon Honesty: Federated Learning Is Not Private. CoRR Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
2020	J	`jnl`	A Survey on Model Watermarking Neural Networks. CoRR Franziska Boenisch
2019	—	`conf`	Applying Differential Privacy to Machine Learning: Challenges and Potentials. Krypto-Tag Franziska Boenisch
2018	J	`jnl`	Tracking All Members of a Honey Bee Colony Over Their Lifetime Using Learned Models of Correspondence. Frontiers Robotics AI Franziska Boenisch, Benjamin Rosemann, Benjamin Wild, David M. Dormagen, Fernando Wario, Tim Landgraf
2018	J	`jnl`	Tracking all members of a honey bee colony over their lifetime. CoRR Franziska Boenisch, Benjamin Rosemann, Benjamin Wild, Fernando Wario, David M. Dormagen, Tim Landgraf