Summer internship positions in the PROBIC group

1. Differentially private machine learning

Background: machine learning, mathematics, programming skills

Differentially private machine learning studies learning methods that can operate while guaranteeing privacy of the data subjects. These methods can be applied to solving predictive learning problems on private data but also for creating provably anonymised data sets. We apply differential privacy in the context of various modern machine learning methods, including Bayesian methods and deep learning.

In this project you will participate in developing and applying new differentially private machine learning methods. Depending on your background, the work will combine working on the mathematical theory of differential privacy, general methods development, implementation and application of the developed methods in different applications.

2. Federated and differentially private deep learning

Supervisors: Antti Koskela, Antti Honkela

Background: machine learning, mathematics, programming skills

Many applications of deep learning require working on distributed data for privacy or efficiency reasons. Federated learning is an example of an algorithm that makes learning in such scenarios more efficient while differential privacy can provide strict privacy guarantees to the data subjects. These learning scenarios require new learning algorithms compared to standard deep learning.

In this project you will participate in developing and applying new learning methods for federated and differentially private deep learning. Depending on your background, the work will combine theoretical work, general methods development, implementation and application of the developed methods in different applications.