DPComp is a tool designed to help assess the accuracy of state-of-the-art differentially private algorithms, it developed by Michael Hay from Colgate University, Ashwin Machanavajjhala from Duke university, and Gerome Miklau from University of Massachussets.
PSI allows researchers upload private data to a secured Dataverse archive, decide what statistics they would like to release about that data, release privacy preserving versions of those statistics to the repository, and interactive queries. It was created by the Privacy Tools for Sharing Research Data project.
OpenMined It is a community focuses in privacy preserving machine learning, peer-to-peer platform for secure, decentralized data science, and a privacy preserving NLP framework. It was created by OpenMined.
A course of differential Privacy , taught by Gautam Kamath from University of Waterloo. This course is on algorithms for differentially private analysis of data, it is theoretically and mathematically based.
Privacy in Statistics and Machine Learning taught by Adam Smith and Jonathan Ullman from Boston University and Northeastern University, respectively. This course explores the following question, How can we learn from a data set of sensitive information while providing meaningful privacy to the individuals whose information it contains?
Private Systems taught by Roxana Geambasu from Columbia University. This course discusses these responsibilities, challenges, and a set of technologies that can be used to enhance privacy.
Algorithms in Society taught by Adam Smith from Boston University. This course looks at the models proposed in the past years to capture societal goals like privacy, fairness, and transparency for algorithms and automated decision system.
Applied Privacy for Data Science taught by James Honaker , Salil Vadhan , Wanrong Zhang from Harvard John A. Paulson School of Engineering and Applied Sciences. This course discusses the risks to privacy when making human subjects data available for research and how to protect against these risks using the formal framework of differential privacy.
Rigorous Approaches to Data Privacy taught by Jonathan Ullman from Boston University. This course explores the following question, How can we enable the analysis of datasets with sensitive information about individuals while protecting the privacy of those individuals?
Mathematical Approaches to Data Privacy taught by Salil Vadhan from Harvard John A. Paulson School of Engineering & Applied Sciences. This course explores the following question, How can we enable the analysis of datasets with sensitive information about individuals while protecting the privacy of those individuals?
Videos
A course of differential Privacy , by Gautam Kamath from University of Waterloo. This course is on algorithms for differentially private analysis of data, it is theoretically and mathematically based.