twistedcubic / coin-press
[NeurIPS 2020] Simple and practical private mean and covariance estimation.
☆33Updated 3 years ago
Related projects: ⓘ
- Code for Auditing DPSGD☆30Updated 2 years ago
- ☆26Updated last year
- ☆21Updated last year
- ☆77Updated 2 years ago
- Computationally friendly hyper-parameter search with DP-SGD☆21Updated last year
- Github pages backend for https://differentialprivacy.org☆25Updated 3 months ago
- Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data☆32Updated 5 years ago
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆64Updated 7 months ago
- ☆16Updated 2 years ago
- Code for fast dpsgd implementations in JAX/TF☆58Updated last year
- Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010☆59Updated 4 years ago
- Research and experimental code related to Opacus, an open-source library for training PyTorch models with Differential Privacy☆17Updated 2 months ago
- Black-Box Ripper: Copying black-box models using generative evolutionary algorithms - NIPS 2020 - Official Implementation☆28Updated 3 years ago
- ☆8Updated 7 years ago
- Official implementation for Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (NeurIPS, 2021).☆22Updated 2 years ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆87Updated 3 months ago
- SAP Security research sample code and tutorials for generating differentially private synthetic datasets using generative deep learning m…☆23Updated 6 months ago
- Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"☆38Updated 5 years ago
- Analytic calibration for differential privacy with Gaussian perturbations☆44Updated 5 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆50Updated 4 years ago
- Differentially Private Clustering in High-Dimensional Euclidean Spaces☆12Updated 6 years ago
- Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19☆34Updated 3 years ago
- Private Adaptive Optimization with Side Information (ICML '22)☆16Updated 2 years ago
- ☆10Updated 2 years ago
- ☆22Updated 5 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆29Updated 2 years ago
- ☆24Updated 2 years ago
- ☆35Updated 2 years ago
- ☆27Updated 2 years ago
- ☆13Updated last year