Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis
Den Heijmans, Author 2, Author 3, Author 4, Author 5
Abstract
This paper presents a scalable framework for enhancing the robustness of multigraph neural networks against adversarial attacks in financial crime analysis.
Reality Card
The study demonstrates that multigraph neural networks are vulnerable to learned structural attacks, and adversarial training can effectively improve their robustness.
Adversarial training consistently improves robustness against learned structural attacks, as shown in experiments on synthetic and realistic AML datasets.
The main limitation is the potential complexity in reproducing the adversarial training framework due to the specific optimization methods used.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.