twistedcubic / coin-press
[NeurIPS 2020] Simple and practical private mean and covariance estimation.
☆33Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for coin-press
- ☆79Updated 2 years ago
- Code for Auditing DPSGD☆35Updated 2 years ago
- ☆10Updated last year
- Computationally friendly hyper-parameter search with DP-SGD☆22Updated 2 years ago
- ☆22Updated last year
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆70Updated 9 months ago
- Research and experimental code related to Opacus, an open-source library for training PyTorch models with Differential Privacy☆17Updated last month
- Github pages backend for https://differentialprivacy.org☆25Updated 5 months ago
- Analytic calibration for differential privacy with Gaussian perturbations☆44Updated 6 years ago
- ☆37Updated 3 years ago
- ☆27Updated last year
- Algorithms for Privacy-Preserving Machine Learning in JAX☆89Updated 5 months ago
- ☆36Updated 2 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆51Updated 4 years ago
- This repo contains the underlying code for all the experiments from the paper: "Automatic Discovery of Privacy-Utility Pareto Fronts"☆26Updated 2 years ago
- Code for fast dpsgd implementations in JAX/TF☆58Updated 2 years ago
- ☆13Updated last year
- Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"☆38Updated 5 years ago
- Black-Box Ripper: Copying black-box models using generative evolutionary algorithms - NIPS 2020 - Official Implementation☆28Updated 4 years ago
- Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19☆34Updated 3 years ago
- ☆22Updated 5 years ago
- Private Adaptive Optimization with Side Information (ICML '22)☆16Updated 2 years ago
- ☆27Updated 2 years ago
- ☆10Updated 2 years ago
- Hadamard Response: Communication efficient, sample optimal, linear time locally private learning of distributions☆14Updated 4 years ago
- Differentially Private Conditional Generative Adversarial Network☆30Updated 3 years ago
- Tilted Empirical Risk Minimization (ICLR '21)☆59Updated last year
- Official implementation for Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (NeurIPS, 2021).☆22Updated 2 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆30Updated 2 years ago
- Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data☆33Updated 5 years ago