Imperceptible Adversarial Attacks on Tabular Data

Vincent Ballet (1, 2) , † Xavier (1) , Jonathan Aigrain (1) , Thibault Laugel (3) , Pascal Frossard (2) , Marcin Detyniecki (1, 4, 3)

1 AXA - Groupe AXA
2 EPFL - Ecole Polytechnique Fédérale de Lausanne
3 LFI - Learning, Fuzzy and Intelligent systems
4 PAN - Polska Akademia Nauk = Polish Academy of Sciences = Académie polonaise des sciences

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.

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Vincent Ballet, † Xavier, Jonathan Aigrain, Thibault Laugel, Pascal Frossard, et al.. Imperceptible Adversarial Attacks on Tabular Data. NeurIPS 2019 Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness and Privacy (Robust AI in FS 2019), Dec 2019, Vancouver, Canada. ⟨hal-03002526⟩