Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis

查看原文 / View Original 编辑 / Edit

Computer Science > Machine Learning arXiv:2610.31718 (cs) [Submitted on 22 Oct 2026] Title: Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis Authors: Dennis Heijmans, H. Çağrı Bilgi, Rui Wang, Kubilay Atasu.

计算机科学 > 机器学习 arXiv:2610.31718 (cs) [提交于 2026 年 10 月 22 日] 标题：面向金融犯罪分析的对抗鲁棒性多图神经网络作者：Dennis Heijmans, H. Çağrı Bilgi, Rui Wang, Kubilay Atasu。

Abstract: Financial transaction networks are naturally represented as multigraphs, where repeated transactions between the same pair of accounts are modeled as distinct edges. Recently proposed multigraph neural network architectures leverage this structure explicitly to achieve a strong performance on anti-money laundering (AML) tasks. However, their robustness to adversaries that manipulate transaction structures to evade detection remains largely unexplored.

摘要：金融交易网络自然地表现为多图，其中同一对账户之间的重复交易被建模为不同的边。最近提出的多图神经网络架构明确利用了这种结构，在反洗钱（AML）任务中取得了强大的性能。然而，它们对于通过操纵交易结构来逃避检测的对抗者的鲁棒性在很大程度上仍未得到探索。

We present the first scalable framework for structural attacks and adversarial training of multigraph neural networks using node-edge incidence matrices, adapting projected gradient descent and projected randomized block coordinate descent methods to optimize structural perturbations over such matrices. We further introduce a cycle-based regularizer that penalizes changes in the global counts of directed 2- and 3-cycles, providing a structural measure of attack plausibility.

我们提出了第一个用于多图神经网络结构攻击和对抗训练的可扩展框架，该框架使用节点-边关联矩阵，并调整了投影梯度下降和投影随机块坐标下降方法，以优化此类矩阵上的结构扰动。我们进一步引入了一种基于循环的正则化器，用于惩罚有向 2-循环和 3-循环全局计数的变化，从而为攻击的合理性提供了一种结构性度量。

Experiments on synthetic pattern-detection and realistic AML datasets show that our learned attacks substantially outperform non-learnable perturbation baselines in reducing detection performance (PR-AUC), while adversarial training consistently improves robustness against these attacks. These results demonstrate that multigraph neural networks are vulnerable to learned structural attacks and that adversarial training provides an effective defense. Our code is available at this https URL.

在合成模式检测和真实 AML 数据集上的实验表明，我们的学习攻击在降低检测性能（PR-AUC）方面显著优于不可学习的扰动基线，而对抗训练则持续提高了针对这些攻击的鲁棒性。这些结果表明，多图神经网络容易受到学习到的结构攻击，而对抗训练提供了一种有效的防御手段。我们的代码可在该 https URL 获取。