Thomas Steinke

120 papers A* 36A 5C 1Misc 1Journal 71Unranked 6
YearRankTypeTitle / Venue / Authors
2025 — conf
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms Under Composition.
SaTML
Christian Janos Lebeda, Matthew Regehr, Gautam Kamath, Thomas Steinke
2025 J jnl
Correlated Noise Mechanisms for Differentially Private Learning.
CoRR
Krishna Pillutla, Jalaj Upadhyay, Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Arun Ganesh, Monika Henzinger, Jonathan Katz, Ryan McKenna, H. Brendan McMahan, Keith Rush, Thomas Steinke, Abhradeep Thakurta
2025 A* conf
Hash-Prune-Invert: Improved Differentially Private Heavy-Hitter Detection in the Two-Server Model.
SP
Borja Balle, James Bell-Clark, Albert Cheu, Adrià Gascón, Jonathan Katz, Mariana Raykova, Phillipp Schoppmann, Thomas Steinke
2025 J jnl
Hush! Protecting Secrets During Model Training: An Indistinguishability Approach.
CoRR
Arun Ganesh, Brendan McMahan, Milad Nasr, Thomas Steinke, Abhradeep Thakurta
2025 A* conf
Near-Exact Privacy Amplification for Matrix Mechanisms.
ICLR
Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque, Thomas Steinke, Abhradeep Guha Thakurta
2025 J jnl
Privately Estimating Black-Box Statistics.
CoRR
Günter F. Steinke, Thomas Steinke
2025 A* conf
Privately Evaluating Untrusted Black-Box Functions.
STOC
Ephraim Linder, Sofya Raskhodnikova, Adam Smith, Thomas Steinke
2025 J jnl
Privately Evaluating Untrusted Black-Box Functions.
CoRR
Ephraim Linder, Sofya Raskhodnikova, Adam Smith, Thomas Steinke
2025 A* conf
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD.
ICLR
Milad Nasr, Thomas Steinke, Borja Balle, Christopher A. Choquette-Choo, Arun Ganesh, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam Smith, Andreas Terzis
2024 J jnl
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition.
CoRR
Christian Janos Lebeda, Matthew Regehr, Gautam Kamath, Thomas Steinke
2024 A* conf
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning.
ICLR
Christopher A. Choquette-Choo, Krishnamurthy Dj Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Guha Thakurta
2024 A conf
Differentially Private Medians and Interior Points for Non-Pathological Data.
ITCS
Maryam Aliakbarpour, Rose Silver, Thomas Steinke, Jonathan R. Ullman
2024 J jnl
Differentially Private Stream Processing at Scale.
Proc. VLDB Endow.
Bing Zhang, Vadym Doroshenko, Peter Kairouz, Thomas Steinke, Abhradeep Thakurta, Ziyin Ma, Eidan Cohen, Himani Apte, Jodi Spacek
2024 J jnl
Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy.
CoRR
Krishnamurthy Dvijotham, H. Brendan McMahan, Krishna Pillutla, Thomas Steinke, Abhradeep Thakurta
2024 J jnl
Hash-Prune-Invert: Improved Differentially Private Heavy-Hitter Detection in the Two-Server Model.
IACR Cryptol. ePrint Arch.
Borja Balle, James Bell, Albert Cheu, Adrià Gascón, Jonathan Katz, Mariana Raykova, Phillipp Schoppmann, Thomas Steinke
2024 J jnl
Near Exact Privacy Amplification for Matrix Mechanisms.
CoRR
Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque, Thomas Steinke, Abhradeep Thakurta
2024 A* conf
Privacy Amplification for Matrix Mechanisms.
ICLR
Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Guha Thakurta
2024 A* conf
Private Geometric Median.
NeurIPS
Mahdi Haghifam, Thomas Steinke, Jonathan R. Ullman
2024 J jnl
Private Geometric Median.
CoRR
Mahdi Haghifam, Thomas Steinke, Jonathan R. Ullman
2024 J jnl
Stealing Part of a Production Language Model.
CoRR
Nicholas Carlini, Daniel Paleka, Krishnamurthy (Dj) Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramèr
2024 A* conf
Stealing part of a production language model.
ICML
Nicholas Carlini, Daniel Paleka, Krishnamurthy Dj Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramèr
2024 J jnl
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD.
CoRR
Thomas Steinke, Milad Nasr, Arun Ganesh, Borja Balle, Christopher A. Choquette-Choo, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam Smith, Andreas Terzis
2023 J jnl
A Bias-Variance-Privacy Trilemma for Statistical Estimation.
CoRR
Gautam Kamath, Argyris Mouzakis, Matthew Regehr, Vikrant Singhal, Thomas Steinke, Jonathan R. Ullman
2023 A conf
Algorithms with More Granular Differential Privacy Guarantees.
ITCS
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thomas Steinke
2023 J jnl
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning.
CoRR
Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
2023 A* conf
Counting Distinct Elements Under Person-Level Differential Privacy.
NeurIPS
Thomas Steinke, Alexander Knop
2023 J jnl
Counting Distinct Elements Under Person-Level Differential Privacy.
CoRR
Alexander Knop, Thomas Steinke
2023 J jnl
Differentially Private Medians and Interior Points for Non-Pathological Data.
CoRR
Maryam Aliakbarpour, Rose Silver, Thomas Steinke, Jonathan R. Ullman
2023 J jnl
Differentially Private Stream Processing at Scale.
CoRR
Bing Zhang, Vadym Doroshenko, Peter Kairouz, Thomas Steinke, Abhradeep Thakurta, Ziyin Ma, Himani Apte, Jodi Spacek
2023 A* conf
Faster Differentially Private Convex Optimization via Second-Order Methods.
NeurIPS
Arun Ganesh, Mahdi Haghifam, Thomas Steinke, Abhradeep Guha Thakurta
2023 J jnl
Faster Differentially Private Convex Optimization via Second-Order Methods.
CoRR
Arun Ganesh, Mahdi Haghifam, Thomas Steinke, Abhradeep Thakurta
2023 J jnl
Privacy Amplification for Matrix Mechanisms.
CoRR
Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
2023 A* conf
Privacy Auditing with One (1) Training Run.
NeurIPS
Thomas Steinke, Milad Nasr, Matthew Jagielski
2023 J jnl
Privacy Auditing with One (1) Training Run.
CoRR
Thomas Steinke, Milad Nasr, Matthew Jagielski
2023 A* conf
Tight Auditing of Differentially Private Machine Learning.
USENIX Security Symposium
Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis
2023 J jnl
Tight Auditing of Differentially Private Machine Learning.
CoRR
Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis
2023 A* conf
Why Is Public Pretraining Necessary for Private Model Training?
ICML
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Guha Thakurta, Lun Wang
2023 J jnl
Why Is Public Pretraining Necessary for Private Model Training?
CoRR
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang
2022 A* conf
A Private and Computationally-Efficient Estimator for Unbounded Gaussians.
COLT
Gautam Kamath, Argyris Mouzakis, Vikrant Singhal, Thomas Steinke, Jonathan R. Ullman
2022 J jnl
Algorithms with More Granular Differential Privacy Guarantees.
CoRR
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thomas Steinke
2022 J jnl
Composition of Differential Privacy & Privacy Amplification by Subsampling.
CoRR
Thomas Steinke
2022 J jnl
Debugging Differential Privacy: A Case Study for Privacy Auditing.
CoRR
Florian Tramèr, Andreas Terzis, Thomas Steinke, Shuang Song, Matthew Jagielski, Nicholas Carlini
2022 J jnl
Discrete Gaussian for Differential Privacy.
J. Priv. Confidentiality
Clément L. Canonne, Gautam Kamath, Thomas Steinke
2022 A* conf
Hyperparameter Tuning with Renyi Differential Privacy.
ICLR
Nicolas Papernot, Thomas Steinke
2022 A* conf
Public Data-Assisted Mirror Descent for Private Model Training.
ICML
Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
2021 J jnl
A Private and Computationally-Efficient Estimator for Unbounded Gaussians.
CoRR
Gautam Kamath, Argyris Mouzakis, Vikrant Singhal, Thomas Steinke, Jonathan R. Ullman
2021 J jnl
Algorithmic Stability for Adaptive Data Analysis.
SIAM J. Comput.
Raef Bassily, Kobbi Nissim, Adam D. Smith, Thomas Steinke, Uri Stemmer, Jonathan R. Ullman
2021 A conf
Evading the Curse of Dimensionality in Unconstrained Private GLMs.
AISTATS
Shuang Song, Thomas Steinke, Om Thakkar, Abhradeep Thakurta
2021 J jnl
Hyperparameter Tuning with Renyi Differential Privacy.
CoRR
Nicolas Papernot, Thomas Steinke
2021 A* conf
Leveraging Public Data for Practical Private Query Release.
ICML
Terrance Liu, Giuseppe Vietri, Thomas Steinke, Jonathan R. Ullman, Zhiwei Steven Wu
2021 J jnl
Leveraging Public Data for Practical Private Query Release.
CoRR
Terrance Liu, Giuseppe Vietri, Thomas Steinke, Jonathan R. Ullman, Zhiwei Steven Wu
2021 A* conf
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes.
COLT
Peter Grünwald, Thomas Steinke, Lydia Zakynthinou
2021 J jnl
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes.
CoRR
Peter Grünwald, Thomas Steinke, Lydia Zakynthinou
2021 J jnl
Private Hypothesis Selection.
IEEE Trans. Inf. Theory
Mark Bun, Gautam Kamath, Thomas Steinke, Zhiwei Steven Wu
2021 A* conf
Privately Learning Subspaces.
NeurIPS
Vikrant Singhal, Thomas Steinke
2021 J jnl
Privately Learning Subspaces.
CoRR
Vikrant Singhal, Thomas Steinke
2021 J jnl
Public Data-Assisted Mirror Descent for Private Model Training.
CoRR
Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
2021 A* conf
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation.
ICML
Peter Kairouz, Ziyu Liu, Thomas Steinke
2021 J jnl
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation.
CoRR
Peter Kairouz, Ziyu Liu, Thomas Steinke
2021 J jnl
The Permute-and-Flip Mechanism is Identical to Report-Noisy-Max with Exponential Noise.
CoRR
Zeyu Ding, Daniel Kifer, Sayed M. Saghaian N. E., Thomas Steinke, Yuxin Wang, Yingtai Xiao, Danfeng Zhang
2020 J jnl
Multi-Central Differential Privacy.
CoRR
Thomas Steinke
2020 A* conf
New Oracle-Efficient Algorithms for Private Synthetic Data Release.
ICML
Giuseppe Vietri, Grace Tian, Mark Bun, Thomas Steinke, Zhiwei Steven Wu
2020 J jnl
New Oracle-Efficient Algorithms for Private Synthetic Data Release.
CoRR
Giuseppe Vietri, Grace Tian, Mark Bun, Thomas Steinke, Zhiwei Steven Wu
2020 A* conf
Open Problem: Information Complexity of VC Learning.
COLT
Thomas Steinke, Lydia Zakynthinou
2020 A* conf
Reasoning About Generalization via Conditional Mutual Information.
COLT
Thomas Steinke, Lydia Zakynthinou
2020 J jnl
Reasoning About Generalization via Conditional Mutual Information.
CoRR
Thomas Steinke, Lydia Zakynthinou
2020 A* conf
The Discrete Gaussian for Differential Privacy.
NeurIPS
Clément L. Canonne, Gautam Kamath, Thomas Steinke
2020 J jnl
The Discrete Gaussian for Differential Privacy.
CoRR
Clément L. Canonne, Gautam Kamath, Thomas Steinke
2019 J jnl
A Hybrid Approach to Privacy-Preserving Federated Learning - (Extended Abstract).
Inform. Spektrum
Stacey Truex, Nathalie Baracaldo, Ali Anwar, Thomas Steinke, Heiko Ludwig, Rui Zhang, Yi Zhou
2019 — conf
A Hybrid Approach to Privacy-Preserving Federated Learning.
AISec@CCS
Stacey Truex, Nathalie Baracaldo, Ali Anwar, Thomas Steinke, Heiko Ludwig, Rui Zhang, Yi Zhou
2019 A* conf
Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation.
NeurIPS
Mark Bun, Thomas Steinke
2019 J jnl
Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation.
CoRR
Mark Bun, Thomas Steinke
2019 J jnl
Make Up Your Mind: The Price of Online Queries in Differential Privacy.
J. Priv. Confidentiality
Mark Bun, Thomas Steinke, Jonathan R. Ullman
2019 A* conf
Private Hypothesis Selection.
NeurIPS
Mark Bun, Gautam Kamath, Thomas Steinke, Zhiwei Steven Wu
2019 J jnl
Private Hypothesis Selection.
CoRR
Mark Bun, Gautam Kamath, Thomas Steinke, Zhiwei Steven Wu
2019 A* conf
Towards Instance-Optimal Private Query Release.
SODA
Jaroslaw Blasiok, Mark Bun, Aleksandar Nikolov, Thomas Steinke
2018 J jnl
A Hybrid Approach to Privacy-Preserving Federated Learning.
CoRR
Stacey Truex, Nathalie Baracaldo, Ali Anwar, Thomas Steinke, Heiko Ludwig, Rui Zhang
2018 A* conf
Calibrating Noise to Variance in Adaptive Data Analysis.
COLT
Vitaly Feldman, Thomas Steinke
2018 A* conf
Composable and versatile privacy via truncated CDP.
STOC
Mark Bun, Cynthia Dwork, Guy N. Rothblum, Thomas Steinke
2018 A* conf
The Limits of Post-Selection Generalization.
NeurIPS
Jonathan R. Ullman, Adam D. Smith, Kobbi Nissim, Uri Stemmer, Thomas Steinke
2018 J jnl
The Limits of Post-Selection Generalization.
CoRR
Kobbi Nissim, Adam D. Smith, Thomas Steinke, Uri Stemmer, Jonathan R. Ullman
2018 J jnl
Towards Instance-Optimal Private Query Release.
CoRR
Jaroslaw Blasiok, Mark Bun, Aleksandar Nikolov, Thomas Steinke
2017 J jnl
Calibrating Noise to Variance in Adaptive Data Analysis.
CoRR
Vitaly Feldman, Thomas Steinke
2017 A* conf
Generalization for Adaptively-chosen Estimators via Stable Median.
COLT
Vitaly Feldman, Thomas Steinke
2017 J jnl
Generalization for Adaptively-chosen Estimators via Stable Median.
CoRR
Vitaly Feldman, Thomas Steinke
2017 A* conf
Make Up Your Mind: The Price of Online Queries in Differential Privacy.
SODA
Mark Bun, Thomas Steinke, Jonathan R. Ullman
2017 J jnl
Pseudorandomness and Fourier-Growth Bounds for Width-3 Branching Programs.
Theory Comput.
Thomas Steinke, Salil P. Vadhan, Andrew Wan
2017 J jnl
Subgaussian Tail Bounds via Stability Arguments.
CoRR
Thomas Steinke, Jonathan R. Ullman
2017 A* conf
Tight Lower Bounds for Differentially Private Selection.
FOCS
Thomas Steinke, Jonathan R. Ullman
2017 J jnl
Tight Lower Bounds for Differentially Private Selection.
CoRR
Thomas Steinke, Jonathan R. Ullman
2016 A* conf
Algorithmic stability for adaptive data analysis.
STOC
Raef Bassily, Kobbi Nissim, Adam D. Smith, Thomas Steinke, Uri Stemmer, Jonathan R. Ullman
2016 J jnl
Between Pure and Approximate Differential Privacy.
J. Priv. Confidentiality
Thomas Steinke, Jonathan R. Ullman
2016 — conf
Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds.
TCC (B1)
Mark Bun, Thomas Steinke
2016 J jnl
Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds.
CoRR
Mark Bun, Thomas Steinke
2016 J jnl
Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds.
IACR Cryptol. ePrint Arch.
Mark Bun, Thomas Steinke
2016 Misc conf
Interactive fingerprinting codes and the hardness of preventing false discovery.
ITA
Thomas Steinke, Jonathan R. Ullman
2016 J jnl
Make Up Your Mind: The Price of Online Queries in Differential Privacy.
CoRR
Mark Bun, Thomas Steinke, Jonathan R. Ullman
2015 J jnl
Algorithmic Stability for Adaptive Data Analysis.
CoRR
Raef Bassily, Kobbi Nissim, Adam D. Smith, Thomas Steinke, Uri Stemmer, Jonathan R. Ullman
2015 J jnl
Between Pure and Approximate Differential Privacy.
CoRR
Thomas Steinke, Jonathan R. Ullman
2015 A* conf
Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery.
COLT
Thomas Steinke, Jonathan R. Ullman
2015 J jnl
Pseudorandomness for Read-Once, Constant-Depth Circuits.
CoRR
Sitan Chen, Thomas Steinke, Salil P. Vadhan
2015 A* conf
Robust Traceability from Trace Amounts.
FOCS
Cynthia Dwork, Adam D. Smith, Thomas Steinke, Jonathan R. Ullman, Salil P. Vadhan
2015 — conf
Weighted Polynomial Approximations: Limits for Learning and Pseudorandomness.
APPROX-RANDOM
Mark Bun, Thomas Steinke
2014 J jnl
Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery.
CoRR
Thomas Steinke, Jonathan R. Ullman
2014 J jnl
Learning Hurdles for Sleeping Experts.
ACM Trans. Comput. Theory
Varun Kanade, Thomas Steinke
2014 J jnl
Pseudorandomness and Fourier Growth Bounds for Width 3 Branching Programs.
CoRR
Thomas Steinke, Salil P. Vadhan, Andrew Wan
2014 J jnl
Pseudorandomness and Fourier Growth Bounds for Width 3 Branching Programs.
Electron. Colloquium Comput. Complex.
Thomas Steinke
2014 — conf
Pseudorandomness and Fourier Growth Bounds for Width-3 Branching Programs.
APPROX-RANDOM
Thomas Steinke, Salil P. Vadhan, Andrew Wan
2014 J jnl
Weighted Polynomial Approximations: Limits for Learning and Pseudorandomness.
CoRR
Mark Bun, Thomas Steinke
2014 J jnl
Weighted Polynomial Approximations: Limits for Learning and Pseudorandomness.
Electron. Colloquium Comput. Complex.
Mark Bun, Thomas Steinke
2013 J jnl
A Rigorous Extension of the Schönhage-Strassen Integer Multiplication Algorithm Using Complex Interval Arithmetic.
Reliab. Comput.
Raazesh Sainudiin, Thomas Steinke
2013 — conf
Pseudorandomness for Regular Branching Programs via Fourier Analysis.
APPROX-RANDOM
Omer Reingold, Thomas Steinke, Salil P. Vadhan
2013 J jnl
Pseudorandomness for Regular Branching Programs via Fourier Analysis.
CoRR
Omer Reingold, Thomas Steinke, Salil P. Vadhan
2013 J jnl
Pseudorandomness for Regular Branching Programs via Fourier Analysis.
Electron. Colloquium Comput. Complex.
Omer Reingold, Thomas Steinke, Salil P. Vadhan
2012 A conf
Hierarchical Heavy Hitters with the Space Saving Algorithm.
ALENEX
Justin Thaler, Michael Mitzenmacher, Thomas Steinke
2012 A conf
Learning hurdles for sleeping experts.
ITCS
Varun Kanade, Thomas Steinke
2012 J jnl
Pseudorandomness for Permutation Branching Programs Without the Group Theory.
Electron. Colloquium Comput. Complex.
Thomas Steinke
2011 J jnl
Hierarchical Heavy Hitters with the Space Saving Algorithm
CoRR
Michael Mitzenmacher, Thomas Steinke, Justin Thaler
2011 J jnl
Learning Hurdles for Sleeping Experts.
Electron. Colloquium Comput. Complex.
Varun Kanade, Thomas Steinke
2010 C conf
A Rigorous Extension of the Schönhage-Strassen Integer Multiplication Algorithm Using Complex Interval Arithmetic
CCA
Thomas Steinke, Raazesh Sainudiin