Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers privacy-preserving data publishing mechanisms, including non-interactive and interactive approaches. It discusses query auditing, simulatable auditing, limitations, and alternative methods like adding noise or perturbing inputs. The concept of differential privacy is introduced, aiming to provide accurate statistics while protecting individual privacy by perturbing query results. Differential privacy ensures minimal risk for individuals joining or leaving a dataset, promoting social utility.