| IBM Federated Learning: An enterprise framework white paper v0.1 H Ludwig, N Baracaldo, G Thomas, Y Zhou, A Anwar, S Rajamoni, Y Ong, ... arXiv preprint arXiv:2007.10987, 2020 | 176 | 2020 |
| Diffprivlib: The IBM differential privacy library N Holohan, S Braghin, P Mac Aonghusa, K Levacher arXiv preprint arXiv:1907.02444, 2019 | 159* | 2019 |
| The bounded Laplace mechanism in differential privacy N Holohan, S Antonatos, S Braghin, P Mac Aonghusa arXiv preprint arXiv:1808.10410, 2018 | 88 | 2018 |
| Optimal differentially private mechanisms for randomised response N Holohan, DJ Leith, O Mason IEEE Transactions on Information Forensics and Security 12 (11), 2726-2735, 2017 | 83 | 2017 |
| Differential privacy in metric spaces: Numerical, categorical and functional data under the one roof N Holohan, DJ Leith, O Mason Information Sciences 305, 256-268, 2015 | 32 | 2015 |
| (,)-Anonymity: -Anonymity with -Differential Privacy N Holohan, S Antonatos, S Braghin, P Mac Aonghusa arXiv preprint arXiv:1710.01615, 2017 | 30 | 2017 |
| Extreme points of the local differential privacy polytope N Holohan, DJ Leith, O Mason Linear Algebra and its Applications 534, 78-96, 2017 | 22 | 2017 |
| Secure random sampling in differential privacy N Holohan, S Braghin Computer Security–ESORICS 2021: 26th European Symposium on Research in …, 2021 | 18 | 2021 |
| Prima: an end-to-end framework for privacy at scale S Antonatos, S Braghin, N Holohan, Y Gkoufas, P Mac Aonghusa 2018 IEEE 34th international conference on data engineering (ICDE), 1531-1542, 2018 | 16 | 2018 |
| Adaptive anonymization of data using statistical inference A Pascale, N Holohan, P Tommasi, S Deparis US Patent App. 16/127,694, 2020 | 12 | 2020 |
| Watermarking anonymized datasets by adding decoys S Antonatos, S Braghin, N Holohan, P MacAonghusa US Patent 10,997,279, 2021 | 8 | 2021 |
| Sensitive data policy recommendation based on compliance obligations of a data source S Antonatos, S Braghin, N Holohan, K Levacher, R Nair, M Stephenson US Patent 11,562,087, 2023 | 6 | 2023 |
| Applying a differential privacy operation on a cluster of data S Antonatos, S Braghin, N Holohan, P Mac Aonghusa US Patent 10,769,306, 2020 | 6 | 2020 |
| (k, ϵ)-anonymity: k-anonymity with ϵ-differential privacy N Holohan, S Antonatos, S Braghin, P Mac Aonghusa Data Privacy@ IBMRisk and Privacy, 2017 | 6 | 2017 |
| Federated Continual Learning with Differentially Private Data Sharing G Zizzo, A Rawat, N Holohan, S Tirupathi Workshop on Federated Learning: Recent Advances and New Challenges (in …, 2022 | 5 | 2022 |
| Detecting unauthorized use of sensitive information in content communicated over a network S Antonatos, S Braghin, N Holohan, P Mac Aonghusa US Patent App. 15/882,583, 2019 | 5 | 2019 |
| Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection SR Kadhe, H Ludwig, N Baracaldo, A King, Y Zhou, K Houck, A Rawat, ... arXiv preprint arXiv:2310.19304, 2023 | 4 | 2023 |
| Secure -Anonymization over Encrypted Databases M Kesarwani, A Kaul, S Braghin, N Holohan, S Antonatos arXiv preprint arXiv:2108.04780, 2021 | 4 | 2021 |
| Mathematical Foundations of Differential Privacy N Holohan Trinity College Dublin, 2017 | 4 | 2017 |
| Differentially private response mechanisms on categorical data N Holohan, DJ Leith, O Mason Discrete Applied Mathematics 211, 86-98, 2016 | 4 | 2016 |
Stefano BraghinIBM ResearchVerified email at ie.ibm.com
