Adaptive Stress Testing for Adversarial Learning in a Financial Environment

TL;DR

This paper applies Adaptive Stress Testing with reinforcement learning to identify vulnerabilities in a financial fraud detection system, revealing failure modes and suggesting improvements to enhance robustness.

Contribution

It introduces a novel application of Adaptive Stress Testing to financial fraud detection, linking failure paths to classifier limits and proposing system augmentations.

Findings

Identified most likely failure paths in fraud detection system

Connected failure modes to classifier limitations

Suggested enhancements to business rules for mitigation

Abstract

We demonstrate the use of Adaptive Stress Testing to detect and address potential vulnerabilities in a financial environment. We develop a simplified model for credit card fraud detection that utilizes a linear regression classifier based on historical payment transaction data coupled with business rules. We then apply the reinforcement learning model known as Adaptive Stress Testing to train an agent, that can be thought of as a potential fraudster, to find the most likely path to system failure -- successfully defrauding the system. We show the connection between this most likely failure path and the limits of the classifier and discuss how the fraud detection system's business rules can be further augmented to mitigate these failure modes.