Imperceptible Adversarial Attacks on Tabular Data

TL;DR

This paper introduces a formal approach to generate imperceptible adversarial examples for tabular data, highlighting security concerns in industrial applications like finance.

Contribution

It formalizes the concept of imperceptibility in tabular adversarial attacks and proposes a method to generate such examples with high fooling rates.

Findings

High fooling rate of generated adversarial examples

Imperceptibility in tabular data is achievable

Applicable to security in financial systems

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.