<ul><li>Graph neural networks (GNNs) are effective tools for fraud detection but are vulnerable to attacks.</li><li>Fraud gangs aim to deceive GNN-based fraud detectors by camouflaging their fraudulent activities.</li><li>This study proposes Multi-target graph injection attacks, targeting spam reviews, fake news, and medical insurance frauds.</li><li>The proposed attack model, MonTi, outperforms existing methods in generating attack nodes and structures.</li></ul>

Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectors

Discover more