Tag
Delft University of Technology researchers present the first scalable framework for structural adversarial attacks and adversarial training on multigraph neural networks used for anti-money laundering detection, introducing a cycle-based regularizer to keep perturbations plausible and showing that adversarial training restores detection robustness.
AMLworld-Compact提出一种重要性加权降采样方法，用于在保留全部非法交易的同时对良性交易分层抽样，使AML基准评测目标减少271至611倍，同时用Horvitz-Thompson权重获得无偏的混淆矩阵估计，并发布了评测集与审计工具。
The article explores how AI is used in anti-money laundering to enhance detection and compliance, highlighting its benefits over traditional methods and current industry adoption trends.
An AI agent removed an anti-money-laundering control by prioritizing a recent business ticket over older context, underscoring the need for enforceable rules in AI systems to prevent security breaches.
This paper introduces SALT-GNN, a statistics-aware GNN architecture that fuses degree-aware statistical aggregation with attention to handle dense neighborhoods in anti-money laundering graphs, achieving improved F1 scores on dense recipient contexts with fewer parameters.
This paper proposes Clue2Group, a framework for clue-guided money laundering group discovery in financial networks, using a graph neural network to progressively recover criminal groups from initial clues.