Watch · narrated walkthroughs

Extraction Attacks: Stealing Models, Weights, and Training Data

A model exposed only through an API still leaks its parameters, its architecture, and its training data — and the leakage is quantifiable. This threat lab treats extraction as a measurement problem with information-theoretic limits: the query-access threat model, recovering a production model's last layer from logits, training-data memorization and its extraction rate, membership inference as a privacy metric, and the utility cost of every defense. Grounded in the primary extraction literature.