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

2024-12-24

AI Summary

This work addresses the problem of coordinated multi-target graph injection attacks launched by fraud rings to evade GNN-based anti-fraud systems—a threat previously unexplored in realistic settings. We propose MonTi, the first practical, one-shot multi-target graph injection attack framework: it employs a Transformer-based architecture to jointly model node attributes and edge generation, and introduces an adaptive budget allocation mechanism to precisely control the connection behavior of each adversarial node. Extensive experiments across five real-world fraud graph datasets demonstrate that MonTi significantly outperforms existing graph injection attacks in stealthiness, attack success rate, and cross-dataset generalizability. Crucially, this study provides the first systematic empirical evidence that coordinated fraud-ring attacks pose a substantial, previously underestimated threat to GNN robustness. Our work establishes a new benchmark for evaluating GNN security and delivers concrete, data-driven insights to inform the design of robust defensive mechanisms.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Graph neural networks (GNNs) have emerged as an effective tool for fraud detection, identifying fraudulent users, and uncovering malicious behaviors. However, attacks against GNN-based fraud detectors and their risks have rarely been studied, thereby leaving potential threats unaddressed. Recent findings suggest that frauds are increasingly organized as gangs or groups. In this work, we design attack scenarios where fraud gangs aim to make their fraud nodes misclassified as benign by camouflaging their illicit activities in collusion. Based on these scenarios, we study adversarial attacks against GNN-based fraud detectors by simulating attacks of fraud gangs in three real-world fraud cases: spam reviews, fake news, and medical insurance frauds. We define these attacks as multi-target graph injection attacks and propose MonTi, a transformer-based Multi-target one-Time graph injection attack model. MonTi simultaneously generates attributes and edges of all attack nodes with a transformer encoder, capturing interdependencies between attributes and edges more effectively than most existing graph injection attack methods that generate these elements sequentially. Additionally, MonTi adaptively allocates the degree budget for each attack node to explore diverse injection structures involving target, candidate, and attack nodes, unlike existing methods that fix the degree budget across all attack nodes. Experiments show that MonTi outperforms the state-of-the-art graph injection attack methods on five real-world graphs.

Problem

• Complex Fraud Gangs
• Multi-Objective Graph Injection Attacks
• Graph Neural Networks Vulnerabilities

Innovation

• MonTi Model
• Multi-Objective Graph Injection Attacks
• Graph Neural Networks (GNNs) Robustness