Designing an attack-defense game: how to increase robustness of financial transaction models via a competition
This addresses security risks for banks using AI in financial decisions, but it is incremental as it adapts existing adversarial attack concepts to a new domain.
The paper tackles the susceptibility of neural networks in financial transaction models to adversarial attacks by proposing a novel competition structure where participants directly oppose each other with attacks and defenses, resulting in a realistic investigation and the introduction of a new open dataset with credit default labels.
Banks routinely use neural networks to make decisions. While these models offer higher accuracy, they are susceptible to adversarial attacks, a risk often overlooked in the context of event sequences, particularly sequences of financial transactions, as most works consider computer vision and NLP modalities. We propose a thorough approach to studying these risks: a novel type of competition that allows a realistic and detailed investigation of problems in financial transaction data. The participants directly oppose each other, proposing attacks and defenses -- so they are examined in close-to-real-life conditions. The paper outlines our unique competition structure with direct opposition of participants, presents results for several different top submissions, and analyzes the competition results. We also introduce a new open dataset featuring financial transactions with credit default labels, enhancing the scope for practical research and development.