Forget Unlearning: Towards True Data-Deletion in Machine Learning

Understand

Unlearning algorithms aim to remove deleted data's influence from trained models at a cost lower than full retraining.

• However, prior guarantees of unlearning in literature are flawed and don't protect the privacy of deleted records.
• We show that when users delete their data as a function of published models, records in a database become interdependent.
• So, even retraining a fresh model after deletion of a record doesn't ensure its privacy.