Differential-Privacy

Differential privacy learning and integration

1. Intuitive explanation

• Differential privacy explaining
• Differential Privacy - Simply Explained
• Differential Privacy A Primer for a Non-technical Audience
• Differential privacy introduction Reading (not so much mathematics, but intuition)
• Laplacian Noisy Counting mechanism illustratioin

2. Academic paper

2.1 Survey

• The Algorithm foundation of Differential Privacy
  • The Algorithm foundation of Differential privacy
  • The Algorithmic Foundations of Privacy Reading community
• Differential privacy and application
  • differential privacy and application
  • Differential privacy and application Reading Notes
• The complexity of differential privacy
• 机器学习隐私保护研究综述-谭作文
• Differentially Private Data Publishing and Analysis: a Survey
• Repository of paper on Differential Privacy
• Paper of Differential Privacy in CCS, S&P, NDSS, USENIX, Infocom
• SoK: Differential Privacies

2.2 Course

• Seminar on differential privacy, Fall 19/20
• CSE 660 Fall 2017
• cs295-data-privacy
• Privacy Study Group
• CS 860 - Algorithms for Private Data Analysis - Fall 2020

2.3 some mechanisms

• Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds

2.4 Differential Privacy in CCS, S&P, NDSS, USENIX, Infocom from 2015-2019 (some of them are from 2020)

• Survey

3. Video

• Recent Development in Differential Privacy II
• Recent Development in Differential Privacy I
• Privacy Amplification by Sampling and Renyi Differential Privacy
• Differential Privacy: From Theory to Practice

4. Code

• 4.0 代码实现DP算法
• 4.1 K-Anonymity Algorithm
• 4.2 Randomized response
• 4.3 Laplace and Exponential Mechanism
• 4.4 Gaussian Mechanism
• 4.5 Google Differential Privacy Library
• 4.6 IBM Differential Privacy Library
• 4.7 Facebook pytorch-dp: Train PyTorch models with Differential Privacy
• 4.8 differential-privacy-federated-learning
• 4.9 PySyft: A library for encrypted, privacy preserving machine learning
• 4.10 PyGrid: A Peer-to-peer Platform for Secure, Privacy-preserving, Decentralized Data Science
• 4.11 PyVacy: Privacy Algorithms for PyTorch
• 4.12 DP-XGBoost: A DP fork of the famous scalable ML engine