How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection. (arXiv:2206.14157v1 [cs.LG])

Model stealing attacks present a dilemma for public machine learning APIs. To
protect financial investments, companies may be forced to withhold important
information about their models that could facilitate theft, including
uncertainty estimates and prediction explanations. This compromise is harmful
not only to users but also to external transparency. Model stealing defenses
seek to resolve this dilemma by making models harder to steal while preserving
utility for benign users. However, existing defenses have poor performance in
practice, either requiring enormous …

adversary lg stealing