bargavj / EvaluatingDPML
This project's goal is to evaluate the privacy leakage of differentially private machine learning models.
☆133Updated 2 years ago
Alternatives and similar repositories for EvaluatingDPML:
Users that are interested in EvaluatingDPML are comparing it to the libraries listed below
- A library for running membership inference attacks against ML models☆144Updated 2 years ago
- Concentrated Differentially Private Gradient Descent with Adaptive per-iteration Privacy Budget☆49Updated 7 years ago
- Differential Privacy Preservation in Deep Learning under Model Attacks☆134Updated 4 years ago
- simple Differential Privacy in PyTorch☆48Updated 4 years ago
- Code for Membership Inference Attack against Machine Learning Models (in Oakland 2017)☆193Updated 7 years ago
- Analytic calibration for differential privacy with Gaussian perturbations☆47Updated 6 years ago
- autodp: A flexible and easy-to-use package for differential privacy☆275Updated last year
- Code to accompany the paper "Deep Learning with Gaussian Differential Privacy"☆49Updated 4 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆31Updated 3 years ago
- Code for "Analyzing Federated Learning through an Adversarial Lens" https://arxiv.org/abs/1811.12470☆150Updated 2 years ago
- Code for Exploiting Unintended Feature Leakage in Collaborative Learning (in Oakland 2019)☆53Updated 5 years ago
- ☆80Updated 2 years ago
- Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models☆125Updated last year
- ☆43Updated 3 years ago
- Implementation of calibration bounds for differential privacy in the shuffle model☆22Updated 4 years ago
- Differential private machine learning☆191Updated 3 years ago
- Implementation of the paper : "Membership Inference Attacks Against Machine Learning Models", Shokri et al.☆60Updated 5 years ago
- This repo implements several algorithms for learning with differential privacy.☆108Updated 2 years ago
- Amortized version of the differentially private SGD algorithm published in "Deep Learning with Differential Privacy" by Abadi et al. Enfo…☆41Updated last year
- Code for NIPS'2017 paper☆50Updated 4 years ago
- Implementation of membership inference and model inversion attacks, extracting training data information from an ML model. Benchmarking …☆103Updated 5 years ago
- Differentially Private Optimization for PyTorch 👁🙅♀️☆186Updated 4 years ago
- The code for "Improved Deep Leakage from Gradients" (iDLG).☆150Updated 4 years ago
- Python package for simple implementations of state-of-the-art LDP frequency estimation algorithms. Contains code for our VLDB 2021 Paper.☆74Updated last year
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆73Updated last year
- DBA: Distributed Backdoor Attacks against Federated Learning (ICLR 2020)☆190Updated 3 years ago
- Code for Auditing DPSGD☆37Updated 3 years ago
- CRFL: Certifiably Robust Federated Learning against Backdoor Attacks (ICML 2021)☆73Updated 3 years ago
- Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch.☆59Updated 7 months ago
- Code for the paper "ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models"☆84Updated 3 years ago