Peter Kairouz

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On ICML 2025 Can LLMs get help from other LLMs without revealing private information? ACL 2024 Improved Communication-Privacy Trade-offs in L_2 Mean Estimation under Streaming Differential Privacy ICML 2024 One-shot Empirical Privacy Estimation for Federated Learning ICLR 2024 Privacy-Preserving Instructions for Aligning Large Language Models ICML 2024 User Inference Attacks on Large Language Models EMNLP 2024 Algorithms for bounding contribution for histogram estimation under user-level privacy ICML 2023 Federated Heavy Hitter Recovery under Linear Sketching ICML 2023 Federated Learning of Gboard Language Models with Differential Privacy ACL 2023 Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation NeurIPS 2023 Private Federated Frequency Estimation: Adapting to the Hardness of the Instance NeurIPS 2023 Private Federated Learning with Autotuned Compression ICML 2023 Unleashing the Power of Randomization in Auditing Differentially Private ML NeurIPS 2023 Optimal Compression of Locally Differentially Private Mechanisms AISTATS 2022 The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning ICML 2022 The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation ICML 2022 Breaking The Dimension Dependence in Sparse Distribution Estimation under Communication Constraints COLT 2021 Estimating Sparse Discrete Distributions Under Privacy and Communication Constraints ALT 2021 (Nearly) Dimension Independent Private ERM with AdaGrad Rates\{via Publicly Estimated Subspaces COLT 2021 Pointwise Bounds for Distribution Estimation under Communication Constraints NeurIPS 2021 Practical and Private (Deep) Learning Without Sampling or Shuffling ICML 2021 Shuffled Model of Differential Privacy in Federated Learning AISTATS 2021 The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation ICML 2021 The Skellam Mechanism for Differentially Private Federated Learning NeurIPS 2021 Breaking the Communication-Privacy-Accuracy Trilemma NeurIPS 2020 Context Aware Local Differential Privacy ICML 2020 Federated Heavy Hitters Discovery with Differential Privacy AISTATS 2020 Generative Models for Effective ML on Private, Decentralized Datasets ICLR 2020 Privacy Amplification via Random Check-Ins NeurIPS 2020 Discrete Distribution Estimation under Local Privacy ICML 2016 Extremal Mechanisms for Local Differential Privacy JMLR 2016 Metadata-conscious anonymous messaging ICML 2016 Secure Multi-party Differential Privacy NeurIPS 2015 The Composition Theorem for Differential Privacy ICML 2015 Extremal Mechanisms for Local Differential Privacy NeurIPS 2014