Background. As AI systems increasingly handle sensitive personal data, ensuring compliance with privacy regulations such as the GDPR—including the right to be forgotten—has become a critical challenge. Traditional deletion methods are often insufficient in machine learning, where sensitive data may be embedded in model parameters. The Forgotten-by-Design approach introduces a proactive privacy-preserving method that prevents sensitive data from being memorized during training. This project builds on that foundation by exploring the generalizability of the method across different datasets and tasks. The work is hosted by RISE Research Institutes of Sweden, a state-owned research institute supporting innovation across academia, industry, and the public sector.

Description. This Master’s thesis project will evaluate the robustness and applicability of the Forgotten-by-Design method in diverse machine learning settings. The student will replicate existing experiments, apply the method to new datasets, and assess its effectiveness in reducing privacy risks while maintaining model performance.

Key Responsibilities

• Literature review on privacy risks in machine learning, especially membership inference attacks and obfuscation techniques like differential privacy.

• Implement the experiments and extend them to new datasets and tasks.

• Analyse privacy risk metrics and model performance trade-offs

• Assess computational feasibility and generalizability of the method.

• Document findings in a scientific report; optionally contribute to open-source tools

Qualifications

• Strong background in mathematics, statistics, and machine learning

• Proficiency in Python and frameworks such as PyTorch or TensorFlow

• Interest in Data privacy, AI regulation, Cyber security and empirical research

Terms

• Scope: 30 hp, one semester full-time

• Location: Luleå (or remote with agreement)

• Start: Flexible

• Compensation: 10,000 SEK for travel, materials and the like after the project is completed and approved

Please note: You need to have a valid student visa that allows you to study in Sweden during the thesis period.

Welcome with your application
Last day of application: July 29
Contact: Rickard Brännvall (rickard.brannvall@ri.se)
Check-in questions (yes/no): 1-5 are required, 6-9 are beneficial, 10 is specifically a plus