Machine Unlearning and Privacy Implications - Differential Privacy for ML

Machine Unlearning and Privacy Implications - Differential Privacy for ML

Explore the privacy implications of machine unlearning in this 50-minute Google TechTalk presented by Mohammad Mahmoody as part of the Differential Privacy for ML seminar series. Delve into the machine learning framework, threat models, and security games associated with deleting inferences and membership inference. Examine theoretical intuitions behind label memorization and reconstruction thread models. Analyze experimental results and discuss deletion compliance in the context of machine learning privacy concerns.