| Advances and open problems in federated learning P Kairouz, HB McMahan, B Avent, A Bellet, M Bennis, AN Bhagoji, ... Foundations and trends® in machine learning 14 (1–2), 1-210, 2021 | 6958 | 2021 |
| The composition theorem for differential privacy P Kairouz, S Oh, P Viswanath IEEE Transactions on Information Theory 63 (6), 4037-4049, 2017 | 851 | 2017 |
| Extremal mechanisms for local differential privacy P Kairouz, S Oh, P Viswanath Journal of Machine Learning Research 17 (17), 1-51, 2016 | 705 | 2016 |
| Can you really backdoor federated learning? Z Sun, P Kairouz, AT Suresh, HB McMahan arXiv preprint arXiv:1911.07963, 2019 | 694 | 2019 |
| Discrete distribution estimation under local privacy P Kairouz, K Bonawitz, D Ramage International Conference on Machine Learning, 2436-2444, 2016 | 406 | 2016 |
| A field guide to federated optimization J Wang, Z Charles, Z Xu, G Joshi, HB McMahan, M Al-Shedivat, G Andrew, ... arXiv preprint arXiv:2107.06917, 2021 | 399 | 2021 |
| Back to the drawing board: A critical evaluation of poisoning attacks on production federated learning V Shejwalkar, A Houmansadr, P Kairouz, D Ramage 2022 IEEE Symposium on Security and Privacy (SP), 1354-1371, 2022 | 323 | 2022 |
| Dp-cgan: Differentially private synthetic data and label generation R Torkzadehmahani, P Kairouz, B Paten Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019 | 288 | 2019 |
| The distributed discrete gaussian mechanism for federated learning with secure aggregation P Kairouz, Z Liu, T Steinke International Conference on Machine Learning, 5201-5212, 2021 | 264 | 2021 |
| Mariana Raykova, Dawn Song, Weikang Song, Sebastian U P Kairouz, HB McMahan, B Avent, A Bellet, M Bennis, AN Bhagoji, ... Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth …, 2021 | 231 | 2021 |
| A general approach to adding differential privacy to iterative training procedures HB McMahan, G Andrew, U Erlingsson, S Chien, I Mironov, N Papernot, ... arXiv preprint arXiv:1812.06210, 2018 | 230 | 2018 |
| Generative models for effective ML on private, decentralized datasets S Augenstein, HB McMahan, D Ramage, S Ramaswamy, P Kairouz, ... arXiv preprint arXiv:1911.06679, 2019 | 228 | 2019 |
| Shuffled model of differential privacy in federated learning A Girgis, D Data, S Diggavi, P Kairouz, AT Suresh International Conference on Artificial Intelligence and Statistics, 2521-2529, 2021 | 220 | 2021 |
| Practical and private (deep) learning without sampling or shuffling P Kairouz, B McMahan, S Song, O Thakkar, A Thakurta, Z Xu International Conference on Machine Learning, 5213-5225, 2021 | 201 | 2021 |
| The staircase mechanism in differential privacy Q Geng, P Kairouz, S Oh, P Viswanath IEEE Journal of Selected Topics in Signal Processing 9 (7), 1176-1184, 2015 | 198 | 2015 |
| Context-aware generative adversarial privacy C Huang, P Kairouz, X Chen, L Sankar, R Rajagopal Entropy 19 (12), 656, 2017 | 183 | 2017 |
| The skellam mechanism for differentially private federated learning N Agarwal, P Kairouz, Z Liu Advances in Neural Information Processing Systems 34, 5052-5064, 2021 | 146 | 2021 |
| Breaking the communication-privacy-accuracy trilemma WN Chen, P Kairouz, A Ozgur Advances in Neural Information Processing Systems 33, 3312-3324, 2020 | 131 | 2020 |
| Federated heavy hitters discovery with differential privacy W Zhu, P Kairouz, B McMahan, H Sun, W Li International Conference on Artificial Intelligence and Statistics, 3837-3847, 2020 | 125 | 2020 |
| Privacy-first health research with federated learning A Sadilek, L Liu, D Nguyen, M Kamruzzaman, S Serghiou, B Rader, ... NPJ digital medicine 4 (1), 132, 2021 | 122 | 2021 |
H. Brendan McMahanResearch Scientist, Google SeattleVerified email at google.com