Privacy-preserving data sharing via probabilistic models
Joonas Jälkö (Ph.D. Student)
Widespread sharing of data would facilitate rapid progress in data science. However, due to privacy constraints, sensitive data cannot be made public. My research aims to learn a generative model from the sensitive data under strict privacy guarantees from differential privacy. The generative model is then used to draw a synthetic twin of the data. My focus is on probabilistic generative models that allow quantifying the uncertainty in the model as well as easy interpretability of the process.
|Primary Host:||Samuel Kaski (Aalto University, Finnish Centre for AI & University of Manchester)|
|Exchange Host:||Mihaela van der Schaar (University of Cambridge, The Alan Turing Institute & University of California)|
|PhD Duration:||16 November 2018 - 16 November 2022|
|Exchange Duration:||- Ongoing - Ongoing|