| A Simple and Practical Algorithm for Private Multivariate Mean and Covariance Estimation | |
| The Discrete Gaussian for Differential Privacy | |
| Private Identity Testing for High-Dimensional Distributions | |
| Differentially-Private Federated Contextual Bandits | |
| Permute-and-Flip: A new mechanism for differentially-private selection | |
| Auditing Differentially Private Machine Learning: How Private is Private SGD? | Introduce a method to measure the emperically achievable value of epsilon. Also introduce an algorithm of poisoning that is effective against SGD clipping |
| AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference | |
| Adversarially Robust Streaming Algorithms via Differential Privacy | |
| Locally Differentially Private (Contextual) Bandits Learning | |
| Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms | |
| On the Equivalence between Online and Private Learnability beyond Binary Classification | |
| A Scalable Approach for Privacy-Preserving Collaborative Machine Learning | |
| Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity | |
| Synthetic Data Generators – Sequential and Private | |
| Smoothly Bounding User Contributions in Differential Privacy | |
| Learning from Mixtures of Private and Public Populations | |
| Smoothed Analysis of Online and Differentially Private Learning | |
| Privacy Amplification via Random Check-Ins | Try to solve the problem of determining the population size when using central DP in FL |
| The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space | |
| Understanding Gradient Clipping in Private SGD: A Geometric Perspective | |
| Differentially Private Clustering: Tight Approximation Ratios | |
| A Computational Separation between Private Learning and Online Learning | |
| Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms | |
| Improving Sparse Vector Technique with Renyi Differential Privacy | |
| Breaking the Communication-Privacy-Accuracy Trilemma | |
| Inverting Gradients - How easy is it to break privacy in federated learning? | Show that FL without DP is vulnerable to reconstruction attack, at least in Computer Vision |
| GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators | sanitize selectively (only the generator) and bounding sensitivity with wasserstein distance instead of clipping. |
| Optimal Private Median Estimation under Minimal Distributional Assumptions | |
| Towards practical differentially private causal graph discovery | |
| Learning discrete distributions: user vs item-level privacy | |
| Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC | |
| CryptoNAS: Private Inference on a ReLU Budget | |
| A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling | |
