J Grana - arXiv e-prints, 2020 - ui.adsabs.harvard.edu
We show how perturbing inputs to machine learning services (ML-service) deployed in the cloud can protect against model stealing attacks. In our formulation, there is an ML-service …
J Grana - arXiv preprint arXiv:2005.05823, 2020 - arxiv.org
We show how perturbing inputs to machine learning services (ML-service) deployed in the cloud can protect against model stealing attacks. In our formulation, there is an ML-service …