| What can we learn privately? SP Kasiviswanathan, HK Lee, K Nissim, S Raskhodnikova, A Smith SIAM Journal on Computing 40 (3), 793-826, 2011 | 1927 | 2011 |
| Composition attacks and auxiliary information in data privacy SR Ganta, SP Kasiviswanathan, A Smith Proceedings of the 14th ACM SIGKDD international conference on Knowledge …, 2008 | 548 | 2008 |
| Subsampled rényi differential privacy and analytical moments accountant YX Wang, B Balle, SP Kasiviswanathan The 22nd international conference on artificial intelligence and statistics …, 2019 | 542 | 2019 |
| Analyzing graphs with node differential privacy SP Kasiviswanathan, K Nissim, S Raskhodnikova, A Smith Theory of Cryptography Conference, 457-476, 2013 | 491 | 2013 |
| Simple Black-Box Adversarial Attacks on Deep Neural Networks. N Narodytska, SP Kasiviswanathan CVPR workshops 2 (2), 2017 | 397 | 2017 |
| Verifying properties of binarized deep neural networks N Narodytska, S Kasiviswanathan, L Ryzhyk, M Sagiv, T Walsh Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018 | 325 | 2018 |
| Simple black-box adversarial perturbations for deep networks N Narodytska, SP Kasiviswanathan arXiv preprint arXiv:1612.06299, 2016 | 299 | 2016 |
| Bounds on the sample complexity for private learning and private data release A Beimel, H Brenner, SP Kasiviswanathan, K Nissim Machine learning 94 (3), 401-437, 2014 | 273 | 2014 |
| Private spatial data aggregation in the local setting R Chen, H Li, AK Qin, SP Kasiviswanathan, H Jin 2016 IEEE 32nd International Conference on Data Engineering (ICDE), 289-300, 2016 | 246 | 2016 |
| On the'semantics' of differential privacy: A bayesian formulation SP Kasiviswanathan, A Smith Journal of Privacy and Confidentiality 6 (1), 2014 | 221 | 2014 |
| Emerging topic detection using dictionary learning SP Kasiviswanathan, P Melville, A Banerjee, V Sindhwani Proceedings of the 20th ACM international conference on Information and …, 2011 | 177 | 2011 |
| The price of privately releasing contingency tables and the spectra of random matrices with correlated rows SP Kasiviswanathan, M Rudelson, A Smith, J Ullman Proceedings of the forty-second ACM symposium on Theory of computing, 775-784, 2010 | 137 | 2010 |
| A note on differential privacy: Defining resistance to arbitrary side information SP Kasiviswanathan, A Smith Cryptology ePrint Archive, 2008 | 115 | 2008 |
| Federated learning under arbitrary communication patterns D Avdiukhin, S Kasiviswanathan International Conference on Machine Learning, 425-435, 2021 | 90 | 2021 |
| Efficient private empirical risk minimization for high-dimensional learning SP Kasiviswanathan, H Jin International Conference on Machine Learning, 488-497, 2016 | 90 | 2016 |
| Algorithms for Counting 2-Sat Solutions and Colorings with Applications M Fürer, SP Kasiviswanathan International Conference on Algorithmic Applications in Management, 47-57, 2007 | 82 | 2007 |
| Streaming anomaly detection using randomized matrix sketching H Huang, SP Kasiviswanathan Proceedings of the VLDB Endowment 9 (3), 192-203, 2015 | 78 | 2015 |
| Efficient and practical stochastic subgradient descent for nuclear norm regularization H Avron, S Kale, S Kasiviswanathan, V Sindhwani arXiv preprint arXiv:1206.6384, 2012 | 78 | 2012 |
| Semi-supervised learning on data streams via temporal label propagation T Wagner, S Guha, S Kasiviswanathan, N Mishra International Conference on Machine Learning, 5095-5104, 2018 | 71 | 2018 |
| Online l1-dictionary learning with application to novel document detection S Kasiviswanathan, H Wang, A Banerjee, P Melville Advances in neural information processing systems 25, 2012 | 68 | 2012 |
Adam SmithProfessor of Computer Science, Boston UniversityVerified email at bu.edu
