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, deep learning and federated 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. The work will involve collaboration with Finnish Center for Artificial Intelligence FCAI Research Programme in Privacy-preserving and Secure AI.

2. Privacy in Health Data Use

Supervisor: Antti Honkela

Background: machine learning, mathematics, programming skills

Secondary use of health data for analytics and research holds great promise for improving our health as well as the healthcare system as a whole, but the sensitive nature of the data requires additional precautions to ensure privacy. Differential privacy provides a promising framework for privacy-preserving data analysis, but more research is urgently needed to understand the practical privacy implications of various algorithms and methods, as well as to develop more flexible privacy-preserving data analysis tools.

In this project you will participate in developing tools for understanding privacy risks in the use of health data and/or tools for facilitating privacy-preserving use of such data. Depending on your background and interests, the work can combine theoretical work, general methods development, implementation and application of the developed methods, as well as collaboration with social scientists and legal scholars. The work will be performed in collaboration with other partners of the Data Literacy for Responsible Decision-Making (DATALIT) project funded by the Strategic Research Council.