A Protection against the Extraction of Neural Network Models

Authors: Hervé Chabanne, Vincent Despiegel, Linda Guiga
Published: 2020-05-26 | Updated: 2020-07-31

Source: https://arxiv.org/abs/2005.12782

PDF: https://arxiv.org/pdf/2005.12782

AIにより推定されたラベル

敵対的攻撃 機械学習技術 機械学習

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

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 keep the underlying NN’s predictions mostly unchanged while complexifying the task of reverse-engineering. Our countermeasure relies on approximating a noisy 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.