cleverhans-lab / capc-iclr
CaPC is a method that enables collaborating parties to improve their own local heterogeneous machine learning models in a setting where both confidentiality and privacy need to be preserved to prevent explicit and implicit sharing of private data.
☆26Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for capc-iclr
- ☆42Updated 3 years ago
- Code for Auditing DPSGD☆35Updated 2 years ago
- ☆33Updated last year
- ☆62Updated 5 years ago
- A machine-learning-based tool for discovering differential privacy violations in black-box algorithms.☆24Updated 2 years ago
- ☆78Updated 2 years ago
- Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010☆59Updated 4 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆30Updated 2 years ago
- Analytic calibration for differential privacy with Gaussian perturbations☆44Updated 6 years ago
- This project's goal is to evaluate the privacy leakage of differentially private machine learning models.☆129Updated last year
- Code for Exploiting Unintended Feature Leakage in Collaborative Learning (in Oakland 2019)☆53Updated 5 years ago
- ☆13Updated last year
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆67Updated 8 months ago
- Privacy Risks of Securing Machine Learning Models against Adversarial Examples☆44Updated 4 years ago
- InstaHide: Instance-hiding Schemes for Private Distributed Learning☆50Updated 4 years ago
- Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"☆38Updated 5 years ago
- ☆23Updated 2 years ago
- Library for training globally-robust neural networks.☆28Updated last year
- This repository contains the codes for first large-scale investigation of Differentially Private Convex Optimization algorithms.☆63Updated 6 years ago
- code for model-targeted poisoning☆11Updated last year
- ☆28Updated last year
- Code for ML Doctor☆86Updated 2 months ago
- ☆45Updated 5 years ago
- Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19☆34Updated 3 years ago
- ☆45Updated 3 years ago
- [CCS 2021] "DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation" by Boxin Wang*, Fan Wu*, Yunhui Long…☆37Updated 2 years ago
- ☆36Updated 2 years ago
- ☆22Updated last month
- Simplicial-FL to manage client device heterogeneity in Federated Learning☆21Updated last year
- Code repo for the paper "Privacy-aware Compression for Federated Data Analysis".☆16Updated last year