Hervé Chabanne, Linda Guiga
Published 2020-05-26Version 1
Given oracle access to a Neural Network (NN), it is possible to extract its underlying model. We here introduce a protection by adding parasitic layers which mostly keep unchanged the underlying NN while complexifying the task of reverse-engineering. Our countermeasure relies on approximating the identity mapping with a Convolutional NN. We explain why the introduction of new parasitic layers complexifies the attacks. We report experiments regarding the performance and the accuracy of the protected NN.
High-Fidelity Extraction of Neural Network Models
Traditional and Heavy-Tailed Self Regularization in Neural Network Models
Model-Centric and Data-Centric Aspects of Active Learning for Neural Network Models
![QR code for arXiv:2005.12782 [cs.LG]](http://oss.arxitics.com/images/favicon.svg)