Detecting Potential Local Adversarial Examples for Human-Interpretable Defense

Authors: Xavier Renard, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
Published: 2018-09-07

Source: https://arxiv.org/abs/1809.02397

PDF: https://arxiv.org/pdf/1809.02397

AIにより推定されたラベル

解釈可能性の損失 モデルの頑健性保証 敵対的移転性

※ 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

Machine learning models are increasingly used in the industry to make decisions such as credit insurance approval. Some people may be tempted to manipulate specific variables, such as the age or the salary, in order to get better chances of approval. In this ongoing work, we propose to discuss, with a first proposition, the issue of detecting a potential local adversarial example on classical tabular data by providing to a human expert the locally critical features for the classifier’s decision, in order to control the provided information and avoid a fraud.