| Stochastic gradient descent with differentially private updates S Song, K Chaudhuri, AD Sarwate 2013 IEEE global conference on signal and information processing, 245-248, 2013 | 615 | 2013 |
| Scalable private learning with pate N Papernot, S Song, I Mironov, A Raghunathan, K Talwar, Ú Erlingsson arXiv preprint arXiv:1802.08908, 2018 | 509 | 2018 |
| Pufferfish privacy mechanisms for correlated data S Song, Y Wang, K Chaudhuri Proceedings of the 2017 ACM International Conference on Management of Data …, 2017 | 141* | 2017 |
| Membership inference attacks from first principles N Carlini, S Chien, M Nasr, S Song, A Terzis, F Tramer 2022 IEEE Symposium on Security and Privacy (SP), 1897-1914, 2022 | 121 | 2022 |
| Tempered sigmoid activations for deep learning with differential privacy N Papernot, A Thakurta, S Song, S Chien, Ú Erlingsson Proceedings of the AAAI Conference on Artificial Intelligence 35 (10), 9312-9321, 2021 | 113* | 2021 |
| Encode, shuffle, analyze privacy revisited: Formalizations and empirical evaluation Ú Erlingsson, V Feldman, I Mironov, A Raghunathan, S Song, K Talwar, ... arXiv preprint arXiv:2001.03618, 2020 | 82 | 2020 |
| Evading the curse of dimensionality in unconstrained private glms S Song, T Steinke, O Thakkar, A Thakurta International Conference on Artificial Intelligence and Statistics, 2638-2646, 2021 | 61* | 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 | 58 | 2021 |
| Renyi differential privacy mechanisms for posterior sampling J Geumlek, S Song, K Chaudhuri Advances in Neural Information Processing Systems 30, 2017 | 56 | 2017 |
| The large margin mechanism for differentially private maximization K Chaudhuri, DJ Hsu, S Song Advances in Neural Information Processing Systems 27, 2014 | 43 | 2014 |
| Learning from data with heterogeneous noise using sgd S Song, K Chaudhuri, A Sarwate Artificial Intelligence and Statistics, 894-902, 2015 | 42 | 2015 |
| Toward training at imagenet scale with differential privacy A Kurakin, S Song, S Chien, R Geambasu, A Terzis, A Thakurta arXiv preprint arXiv:2201.12328, 2022 | 29 | 2022 |
| Combining mixmatch and active learning for better accuracy with fewer labels S Song, D Berthelot, A Rostamizadeh arXiv preprint arXiv:1912.00594, 2019 | 27 | 2019 |
| Differentially private continual release of graph statistics S Song, S Little, S Mehta, S Vinterbo, K Chaudhuri arXiv preprint arXiv:1809.02575, 2018 | 20 | 2018 |
| The flajolet-martin sketch itself preserves differential privacy: Private counting with minimal space A Smith, S Song, A Guha Thakurta Advances in Neural Information Processing Systems 33, 19561-19572, 2020 | 18 | 2020 |
| 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 | 16 | 2022 |
| Composition properties of inferential privacy for time-series data S Song, K Chaudhuri 2017 55th Annual Allerton Conference on Communication, Control, and …, 2017 | 16 | 2017 |
| That which we call private Ú Erlingsson, I Mironov, A Raghunathan, S Song arXiv preprint arXiv:1908.03566, 2019 | 15 | 2019 |
| Differentially private model personalization P Jain, J Rush, A Smith, S Song, A Guha Thakurta Advances in Neural Information Processing Systems 34, 29723-29735, 2021 | 13 | 2021 |
| Private alternating least squares: Practical private matrix completion with tighter rates S Chien, P Jain, W Krichene, S Rendle, S Song, A Thakurta, L Zhang International Conference on Machine Learning, 1877-1887, 2021 | 10 | 2021 |
