Privacy Preserving Machine Learning Techniques
Title: Privacy Preserving Machine Learning Techniques
DNr: Berzelius-2023-166
Project Type: LiU Berzelius
Principal Investigator: Saloni Kwatra <>
Affiliation: Umeå universitet
Duration: 2023-06-15 – 2024-01-01
Classification: 10201


Attacking machine learning models is one of the many ways to measure the privacy of machine learning models. Therefore, studying the performance of attacks against machine learning techniques is essential to know whether somebody can share information about machine learning models, and if shared, how much can be shared? Therefore, our work aims to answer how much information about machine learning models is safe to disclose while protecting users' privacy.