Imperceptible Adversarial Attacks on Tabular Data

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.

presented at NeurIPS 2019 Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy (Robust AI in FS 2019), Vancouver, Canada

Cited by in corpus (11)

• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecards
• When and How to Fool Explainable Models (and Humans) with Adversarial Examples
• Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data
• Not All Datasets Are Born Equal: On Heterogeneous Data and Adversarial Examples
• The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples
• Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis
• Adversarial Robustness with Non-uniform Perturbations
• Leaking Sensitive Financial Accounting Data in Plain Sight using Deep Autoencoder Neural Networks
• Adaptive Adversarial Training Does Not Increase Recourse Costs
• Generalized Adversarial Distances to Efficiently Discover Classifier Errors