| Monte carlo and reconstruction membership inference attacks against generative models B Hilprecht, M Härterich, D Bernau Proceedings on Privacy Enhancing Technologies, 2019 | 211 | 2019 |
| Anonymization techniques to protect data C Hebert, D Bernau, A Lahouel US Patent 10,628,608, 2020 | 70 | 2020 |
| Assessing differentially private deep learning with membership inference D Bernau, PW Grassal, J Robl, F Kerschbaum arXiv preprint arXiv:1912.11328, 2019 | 35 | 2019 |
| Comparing local and central differential privacy using membership inference attacks D Bernau, J Robl, PW Grassal, S Schneider, F Kerschbaum IFIP Annual Conference on Data and Applications Security and Privacy, 22-42, 2021 | 31 | 2021 |
| The influence of differential privacy on short term electric load forecasting G Eibl, K Bao, PW Grassal, D Bernau, H Schmeck Energy Informatics 1 (Suppl 1), 48, 2018 | 22 | 2018 |
| Privacy-preserving outlier detection for data streams J Böhler, D Bernau, F Kerschbaum IFIP Annual Conference on Data and Applications Security and Privacy, 225-238, 2017 | 22 | 2017 |
| Providing differentially private data with causality preservation W Beskorovajnov, D Bernau US Patent 10,423,781, 2019 | 21 | 2019 |
| Tracking privacy budget with distributed ledger D Bernau, F Hahn, J Boehler US Patent 10,380,366, 2019 | 19 | 2019 |
| Differential privacy and outlier detection within a non-interactive model J Boehler, D Bernau, F Kerschbaum US Patent 10,445,527, 2019 | 15 | 2019 |
| On the privacy–utility trade-off in differentially private hierarchical text classification D Wunderlich, D Bernau, F Aldà, J Parra-Arnau, T Strufe Applied Sciences 12 (21), 11177, 2022 | 14 | 2022 |
| Quantifying identifiability to choose and audit in differentially private deep learning D Bernau, G Eibl, PW Grassal, H Keller, F Kerschbaum arXiv preprint arXiv:2103.02913, 2021 | 14 | 2021 |
| Interpretability framework for differentially private deep learning D Bernau, PW Grassal, H Keller, M Haerterich US Patent 12,001,588, 2024 | 11 | 2024 |
| Assessing differentially private variational autoencoders under membership inference D Bernau, J Robl, F Kerschbaum IFIP Annual Conference on Data and Applications Security and Privacy, 3-14, 2022 | 9 | 2022 |
| Selective access for supply chain management in the cloud A Tueno, F Kerschbaum, D Bernau, S Foresti 2017 IEEE Conference on Communications and Network Security (CNS), 476-482, 2017 | 8 | 2017 |
| Reconstruction and membership inference attacks against generative models B Hilprecht, M Härterich, D Bernau arXiv preprint arXiv:1906.03006, 2019 | 6 | 2019 |
| Privacy preserving smart metering D Bernau, PW Grassal, F Kerschbaum US Patent 10,746,567, 2020 | 5 | 2020 |
| Differential privacy to prevent machine learning model membership inference D Bernau, J Robl, PW Grassal, F Kerschbaum US Patent 11,449,639, 2022 | 3 | 2022 |
| Accurately identifying members of training data in variational autoencoders by reconstruction error B Hilprecht, D Bernau, M Haerterich US Patent 11,501,172, 2022 | 2 | 2022 |
| INTERPRETABILITY FRAMEWORK FOR DIFFERENTIALLY PRIVATE DEEP LEARNING D Bernau, P Grassal, H Keller, M Haerterich US Patent App. 18/904,462, 2025 | | 2025 |
| Interpretability framework for differentially private deep learning D Bernau, PW Grassal, H Keller, M Haerterich US Patent 12,147,577, 2024 | | 2024 |
Florian KerschbaumUniversity of Waterloo在 uwaterloo.ca 的電子郵件地址已通過驗證