Imperceptible Adversarial Attacks on Tabular Data

Authors: Vincent Ballet, Xavier Renard, Jonathan Aigrain, Thibault Laugel, Pascal Frossard, Marcin Detyniecki
Published: 2019-11-08 | Updated: 2019-12-13

Source: https://arxiv.org/abs/1911.03274

PDF: https://arxiv.org/pdf/1911.03274

AIにより推定されたラベル

敵対的サンプル 敵対的攻撃 タブularデータの脆弱性

※ 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

Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions. While research on the topic has mainly been focusing on the image domain, numerous industrial applications, in particular in finance, rely on standard tabular data. In this paper, we discuss the notion of adversarial examples in the tabular domain. We propose a formalization based on the imperceptibility of attacks in the tabular domain leading to an approach to generate imperceptible adversarial examples. Experiments show that we can generate imperceptible adversarial examples with a high fooling rate.