A Framework for Understanding Model Extraction Attack and Defense. (arXiv:2206.11480v1 [cs.LG])

Web: http://arxiv.org/abs/2206.11480

The privacy of machine learning models has become a significant concern in
many emerging Machine-Learning-as-a-Service applications, where prediction
services based on well-trained models are offered to users via pay-per-query.
The lack of a defense mechanism can impose a high risk on the privacy of the
server's model since an adversary could efficiently steal the model by querying
only a few `good' data points. The interplay between a server's defense and an
adversary's attack inevitably leads to an arms race dilemma, …

arxiv defense extraction framework lg model understanding