Welcome to the Differential Privacy Learning Hub! This hub serves as a curated collection of resources related to the field of Differential Privacy. Here you can find important papers, books, repositories, and links to communities, universities, and companies actively involved in Differential Privacy research and implementation.
- Papers
- Books
- Repositories
- Blog Posts & Articles
- Talks & Presentations
- Community Links
- Data Resources
- Attacks
- The Algorithmic Foundations of Differential Privacy - Cynthia Dwork and Aaron Roth (2006)
- How to DP-fy ML: A Practical Guide to Machine Lear - Natalia Ponomareva, Hussein Hazimeh, Alex Kurakin, Zheng Xu, Carson Denison, H. Brendan McMahan, Sergei Vassilvitskii, Steve Chien, Abhradeep Thakurta (2023)
- PAC Privacy: Automatic Privacy Measurement and Control of Data Processing - Hanshen Xiao (2023)
- Public Data-Assisted Mirror Descent for Private Model Training - Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta (2022)
- Data Synthesis via Differentially Private Markov Random Fields - Kuntai Cai, Jianxin Wei, Xiaokui Xiao, Xiaoyu Lei (2014)
- Robust De-anonymization of Large Sparse Datasets - rvind Narayanan, Vitaly Shmatikov (2006)
- PATE-GAN: GENERATING SYNTHETIC DATA WITH DIFFERENTIAL PRIVACY GUARANTEES - James Jordon, Mihaela van der Schaar, Jinsung Yoon (2019)
- G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators - Yunhui Long, Boxin Wang, Zhuolin Yang, Bhavya Kailkhura, Aston Zhang (2021)
- ONLINE DIFFERENTIALLY PRIVATE SYNTHETIC DATA GENERATION - YIYUN HE, ROMAN VERSHYNIN, AND YIZHE ZHU (2024)
- RAPPOR: Randomized Aggregatable Privacy-Preserving - Úlfar Erlingsson, Vasyl Pihur, Aleksandra Korolova (2014)
- Privacy-Preserving Load Forecasting via Personalized Model Obfuscation - Shourya Bose, Yu Zhang, Kibaek Kim (2016)
- PrivBayes: Private Data Release via Bayesian Networks - JUN ZHANG,GRAHAM CORMODE (??)
- Differentially Private Generative Adversarial Network - Liyang Xie, Kaixiang Lin, Shu Wang, Fei Wang, Jiayu Zhou (2018)
- PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Models - Haiming Wang, Zhikun Zhang, Tianhao Wang, Shibo He, Michael Backes, Jiming Chen, Yang Zhang (2022)
- Group and Attack: Auditing Differential Privacy - Johan Lokna, Dimitar I. Dimitrov, Anouk Paradis, Martin Vechev
- Privacy Loss Classes: The Central Limit Theorem in Differential Privacy - David M. Sommer, Sebastian Meiser, and Esfandiar Mohammad (2019)
- A Differential Privacy Budget Allocation Algorithm Based on Out-of-Bag Estimation in Random Forest - Xin Li, Baodong Qin,ORCID,Yiyuan Luo, and Dong Zheng (2022)
- Differentially Private High-Dimensional Data Publication via Sampling-Based Inference - (2015)
- PSI (Ψ): a Private data Sharing Interface - Marco Gaboardi, James Honaker, Gary King, Jack Murtagh, Kobbi Nissim, Jonathan Ullman, Salil Vadhan (2018)
- Federated Learning and Privacy - BY KALLISTA BONAWITZ, PETER KAIROUZ, BRENDAN MCMAHAN, AND DANIEL RAMAGE (2022)
- Assessing the risk of re-identification arising from an attack on anonymised data - Anna Antoniou, Giacomo Dossena, Julia MacMillan, Steven Hamblin, David Clifton, Paula Petrone (2022)
- Programming Differential Privacy - Programming Differential Privacy uses examples and Python code to explain the ideas behind differential privacy! The book is suitable for undergraduate students in computer science, and no theory background is expected.
- ...
- Diffprivlib - IBM: Diffprivlib is a general-purpose library for experimenting with, investigating and developing applications in, differential privacy.
- differential-privacy - Google: This repository contains libraries to generate ε- and (ε, δ)-differentially private statistics over datasets.
- PyDP - OpenMined: A Python wrapper for Google's Differential Privacy project.
- Opacus - Meta & Pytorch: a library that enables training PyTorch models with differential privacy.
- OpenDP - Harvard: a modular collection of statistical algorithms that adhere to the definition of differential privacy.
- An Introduction to Differential Privacy
- Differential privacy: Pros and cons of enterprise use cases
- Lecture 1: Introduction to Differential Privacy and the Laplace Mechanism
- Meta
- Tryolabs
- Medium: Understand DP
- Medium: What is DP?
- Ydata: What is DP?
- Ydata: Why Data Sharing?
- Neptune
- ANONOS: What is Differential Privacy: definition, mechanisms, and examples
- Differential privacy: its technological prescriptive using big data
- Prof. Cynthia Dwork | Rothschild Lecture: The Promise of Differential Privacy
- Differential Privacy: Simply Explained
- Deep Learning with Differential Privacy (DP-SGD explained)
- Privacy Preserving AI (Andrew Trask) | MIT Deep Learning Series
- OpenDP Organization - OpenDP is a community effort to build trustworthy, open-source software tools for statistical analysis of sensitive private data.
- Ted's Blog - A blog about privacy, research, and privacy research.
- TPDP 2024 - Theory and Practice of Differential Privacy - Boston - August 20-21, 2024
- The 'Re-Identification' of Governor William Weld's Medical Information - 1997
- & Study- 2000
- Netflix Prize Case - 2006
- AOL log search - 2006
- Harvard Professor Re-Identifies Anonymous Volunteers In DNA Study - 2013
- Taxi trips made in New York City - 2014
- Twitter Metadata - 2015
- Medicare Benefits Schedule and Pharmaceutical Benefits Schedule - 2016
- Strava - 2017
- Cambridge Analytica & Cambridge Analytica - 2018
- Family Planning NSW - 2018
- Public Transport Victoria - 2018
- The Federal Court published the names of people who said they had been persecuted in their home countries, potentially putting them at risk - 2020
- Membership Inference Attacks against Machine Learning Models - Reza Shokri, Marco Stronati, Congzheng Song, Vitaly Shmatikov(2017)
- PrivPkt: Privacy Preserving Collaborative Encrypted Traffic Classification
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
- On k-Anonymity and the Curse of Dimensionality
- ML Privacy Meter
- ML-Doctor
- PrivPkt
- Clever-Hans, and its blog
If you have suggestions for additional resources or improvements to the repository, feel free to open an issue or submit a pull request.