In conventional machine learning, data needs to be collected then used to train a model. Federated learning enables distributed users to build a model collaboratively without sharing their sensitive data with others. However, applying federated learning widens the attack surface against the built model.
I am offering a number of open thesis positions to tackle this problem. Interested students from Informatics, mathematics, and physics, are encouraged to apply. The exact details of the thesis topic can be decided according to the available topics, competences, and interests of the student.
- Interested in neural networks and privacy/security
- Programming skills (preferable Python)
https://ai.googleblog.com/2017/04/feder ... ative.html
Supervisor: Aidmar Wainakh, firstname.lastname@example.org
Please start your email title with: [THESIS APPLICANT]