Imperceptible Adversarial Attacks on Tabular Data
This addresses security concerns for machine learning models in industrial applications like finance, though it is incremental by extending adversarial attack research from images to tabular data.
The paper tackles the problem of adversarial attacks on tabular data, proposing a method to generate imperceptible adversarial examples that achieve a high fooling rate in experiments.
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.