Follow
Lukas Wutschitz
Lukas Wutschitz
Verified email at microsoft.com
Title
Cited by
Cited by
Year
Differentially private fine-tuning of language models
D Yu, S Naik, A Backurs, S Gopi, HA Inan, G Kamath, J Kulkarni, YT Lee, ...
arXiv preprint arXiv:2110.06500, 2021
2132021
Numerical composition of differential privacy
S Gopi, YT Lee, L Wutschitz
Advances in Neural Information Processing Systems 34, 11631-11642, 2021
1192021
Analyzing information leakage of updates to natural language models
S Zanella-Béguelin, L Wutschitz, S Tople, V Rühle, A Paverd, ...
Proceedings of the 2020 ACM SIGSAC conference on computer and communications …, 2020
1032020
Analyzing leakage of personally identifiable information in language models
N Lukas, A Salem, R Sim, S Tople, L Wutschitz, S Zanella-Béguelin
2023 IEEE Symposium on Security and Privacy (SP), 346-363, 2023
822023
Training data leakage analysis in language models
HA Inan, O Ramadan, L Wutschitz, D Jones, V Rühle, J Withers, R Sim
arXiv preprint arXiv:2101.05405, 2021
282021
Bayesian estimation of differential privacy
S Zanella-Béguelin, L Wutschitz, S Tople, A Salem, V Rühle, A Paverd, ...
International Conference on Machine Learning, 40624-40636, 2023
272023
A full-field simulation methodology for sonic boom modeling on adaptive Cartesian cut-cell meshes
R Yamashita, L Wutschitz, N Nikiforakis
Journal of Computational Physics 408, 109271, 2020
122020
Differentially private model compression
F Mireshghallah, A Backurs, HA Inan, L Wutschitz, J Kulkarni
Advances in Neural Information Processing Systems 35, 29468-29483, 2022
112022
Privacy analysis in language models via training data leakage report
HA Inan, O Ramadan, L Wutschitz, D Jones, V Rühle, J Withers, R Sim
ArXiv, abs/2101.05405, 2021
92021
dp-transformers: Training transformer models with differential privacy
L Wutschitz, HA Inan, A Manoel
72022
Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective
L Wutschitz, B Köpf, A Paverd, S Rajmohan, A Salem, S Tople, ...
arXiv preprint arXiv:2311.15792, 2023
32023
Analyzing information leakage of updates to natural language models
M Brockschmidt, B Köpf, O Ohrimenko, A Paverd, V Rühle, S Tople, ...
arXiv e-prints, arXiv: 1912.07942, 2019
12019
A Cartesian Cut-Cell Approach for Modelling Air and Water Droplet Flow
L Wutschitz, N Nikiforakis
54th AIAA Aerospace Sciences Meeting, 0600, 2016
12016
Closed-Form Bounds for DP-SGD against Record-level Inference
G Cherubin, B Köpf, A Paverd, S Tople, L Wutschitz, S Zanella-Béguelin
arXiv preprint arXiv:2402.14397, 2024
2024
On a Cartesian cut-cell methodology for simulating atmospheric ice accretion on aircraft
L Wutschitz
2020
The system can't perform the operation now. Try again later.
Articles 1–15