| When the Curious Abandon Honesty: Federated Learning Is Not Private F Boenisch, A Dziedzic, R Schuster, AS Shamsabadi, I Shumailov, ... Proceedings of the 8th IEEE European Symposium on Security and Privacy, 2023 | 216* | 2023 |
| Testing robustness against unforeseen adversaries M Kaufmann, D Kang, Y Sun, S Basart, X Yin, M Mazeika, A Arora, ... arXiv preprint arXiv:1908.08016, 2019 | 152* | 2019 |
| A Systematic Review on Model Watermarking for Neural Networks F Boenisch Frontiers in Big Data 4, 96, 2021 | 119 | 2021 |
| Tracking all members of a honey bee colony over their lifetime using learned models of correspondence F Boenisch, B Rosemann, B Wild, D Dormagen, F Wario, T Landgraf Frontiers in Robotics and AI 5, 35, 2018 | 75 | 2018 |
| Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models H Duan, A Dziedzic, N Papernot, F Boenisch Advances in Neural Information Processing Systems 36, 2023 | 72 | 2023 |
| A Unified Framework for Quantifying Privacy Risk in Synthetic Data M Giomi, F Boenisch, C Wehmeyer, B Tasnádi 23rd Privacy Enhancing Technologies Symposium (PETs'23), 2023 | 53 | 2023 |
| On the Privacy Risk of In-context Learning H Duan, A Dziedzic, M Yaghini, N Papernot, F Boenisch The 61st Annual Meeting Of The Association For Computational Linguistics, 2023 | 38 | 2023 |
| From Differential Privacy to Bounds on Membership Inference: Less can be More A Thudi, I Shumailov, F Boenisch, N Papernot Transactions on Machine Learning Research, 2024 | 30* | 2024 |
| Dataset Inference for Self-Supervised Models A Dziedzic, H Duan, MA Kaleem, N Dhawan, J Guan, Y Cattan, ... NeurIPS (Neural Information Processing Systems), 2022 | 30 | 2022 |
| “I Never Thought About Securing My Machine Learning Systems”: A Study of Security and Privacy Awareness of Machine Learning Practitioners F Boenisch, V Battis, N Buchmann, M Poikela Mensch und Computer 2021, 520-546, 2021 | 29 | 2021 |
| Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning F Boenisch, P Sperl, K Böttinger arXiv preprint arXiv:2105.07985, 2021 | 25 | 2021 |
| Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation F Boenisch, A Dziedzic, R Schuster, AS Shamsabadi, I Shumailov, ... Proceedings of the 8th IEEE European Symposium on Security and Privacy, 2023 | 19* | 2023 |
| Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees F Boenisch, C Mühl, R Rinberg, J Ihrig, A Dziedzic 23rd Privacy Enhancing Technologies Symposium (PETs'23), 2023 | 19 | 2023 |
| Toward sharing brain images: Differentially private TOF-MRA images with segmentation labels using generative adversarial networks T Kossen, MA Hirzel, VI Madai, F Boenisch, A Hennemuth, K Hildebrand, ... Frontiers in artificial intelligence 5, 813842, 2022 | 16 | 2022 |
| Have it your way: Individualized Privacy Assignment for DP-SGD F Boenisch, C Mühl, A Dziedzic, R Rinberg, N Papernot Advances in Neural Information Processing Systems 36, 2023 | 14 | 2023 |
| Side-Channel Attacks on Query-Based Data Anonymization F Boenisch, R Munz, M Tiepelt, S Hanisch, C Kuhn, P Francis Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications …, 2021 | 13 | 2021 |
| Learning to Walk Impartially on the Pareto Frontier of Fairness, Privacy, and Utility M Yaghini, P Liu, F Boenisch, N Papernot NeurIPS 2023 Workshop on Regulatable ML, 2023 | 10* | 2023 |
| Privatsphäre und Maschinelles Lernen: Über Gefahren und Schutzmaßnahmen F Boenisch Datenschutz und Datensicherheit-DuD 45, 448-452, 2021 | 8 | 2021 |
| Memorization in Self-Supervised Learning Improves Downstream Generalization W Wang, MA Kaleem, A Dziedzic, M Backes, N Papernot, F Boenisch International Conference on Learning Representations (ICLR), 2024 | 7 | 2024 |
| Sentence Embedding Encoders are Easy to Steal but Hard to Defend A Dziedzic, F Boenisch, M Jiang, H Duan, N Papernot ICLR 2023 Workshop on Pitfalls of limited data and computation for …, 2023 | 7 | 2023 |
Adam DziedzicSprintML group at CISPA, Vector Institute & University of TorontoEmail verificata su cispa.de