Beyond Labeling Oracles: What does it mean to steal ML models?

arXiv:2310.01959v3 Announce Type: replace-cross
Abstract: Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. Machine Learning (ML) models are expensive to train, in part because data is hard to obtain, and a primary incentive for model extraction is to acquire a model while incurring less cost than training from scratch. Literature on model extraction commonly claims or presumes that the attacker is able to save on …

access apis arxiv as-a-service attacks beyond cs.cr cs.lg data extraction hard labeling machine machine learning ml models model extraction offer query service service providers steal train