Follow
Thomas Steinke
Thomas Steinke
Google DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Stealing Part of a Production Language Model
N Carlini, D Paleka, KD Dvijotham, T Steinke, J Hayase, AF Cooper, ...
arXiv preprint arXiv:2403.06634, 2024
12024
Counting Distinct Elements Under Person-Level Differential Privacy
T Steinke, A Knop
Advances in Neural Information Processing Systems 36, 2024
2024
Faster differentially private convex optimization via second-order methods
A Ganesh, M Haghifam, T Steinke, A Guha Thakurta
Advances in Neural Information Processing Systems 36, 2024
52024
Privacy auditing with one (1) training run
T Steinke, M Nasr, M Jagielski
Advances in Neural Information Processing Systems 36, 2024
212024
Privacy Amplification for Matrix Mechanisms
CA Choquette-Choo, A Ganesh, T Steinke, A Thakurta
arXiv preprint arXiv:2310.15526, 2023
22023
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
CA Choquette-Choo, K Dvijotham, K Pillutla, A Ganesh, T Steinke, ...
arXiv preprint arXiv:2310.06771, 2023
42023
Why Is Public Pretraining Necessary for Private Model Training?
A Ganesh, M Haghifam, M Nasr, S Oh, T Steinke, O Thakkar, AG Thakurta, ...
International Conference on Machine Learning, 10611-10627, 2023
262023
Differentially Private Medians and Interior Points for Non-Pathological Data
M Aliakbarpour, R Silver, T Steinke, J Ullman
arXiv preprint arXiv:2305.13440, 2023
2023
Leveraging Public Data in Training Neural Networks with Private Mirror Descent
OD Thakkar, E Amid, A Ganesh, R Mathews, S Ramaswamy, S Song, ...
US Patent App. 17/937,825, 2023
2023
Differentially Private Stream Processing at Scale
B Zhang, V Doroshenko, P Kairouz, T Steinke, A Thakurta, Z Ma, H Apte, ...
arXiv preprint arXiv:2303.18086, 2023
32023
A Bias-Variance-Privacy Trilemma for Statistical Estimation
G Kamath, A Mouzakis, M Regehr, V Singhal, T Steinke, J Ullman
arXiv preprint arXiv:2301.13334, 2023
102023
Tight auditing of differentially private machine learning
M Nasr, J Hayes, T Steinke, B Balle, F Tramèr, M Jagielski, N Carlini, ...
32nd USENIX Security Symposium (USENIX Security 23), 1631-1648, 2023
302023
Algorithms with More Granular Differential Privacy Guarantees
B Ghazi, R Kumar, P Manurangsi, T Steinke
ITCS, 2023
12023
Composition of Differential Privacy & Privacy Amplification by Subsampling
T Steinke
arXiv preprint arXiv:2210.00597, 2022
242022
A Private and Computationally-Efficient Estimator for Unbounded Gaussians
G Kamath, A Mouzakis, V Singhal, T Steinke, J Ullman
Conference on Learning Theory, 544-572, 2022
342022
Public data-assisted mirror descent for private model training
E Amid, A Ganesh, R Mathews, S Ramaswamy, S Song, T Steinke, ...
International Conference on Machine Learning, 517-535, 2022
462022
Differentially Private Linear Regression via Medians
A Knop, T Steinke
OpenReview, JSBgIaxAXk9, 2022
2022
Debugging Differential Privacy: A Case Study for Privacy Auditing
F Tramer, A Terzis, T Steinke, S Song, M Jagielski, N Carlini
arXiv preprint arXiv:2202.12219, 2022
272022
Privately learning subspaces
V Singhal, T Steinke
Advances in Neural Information Processing Systems 34, 1312-1324, 2021
192021
Private and federated learning
NB Angel, S Truex, HH Ludwig, A Anwar, T Steinke, R Zhang
US Patent 11,139,961, 2021
22021
The system can't perform the operation now. Try again later.
Articles 1–20