TAS-GNN: A Status-Aware Signed Graph Neural Network for Anomaly Detection in Bitcoin Trust Systems

Researchers developed TAS-GNN, a novel Graph Neural Network framework specifically designed to detect fraudulent behavior in Bitcoin trust systems. The system addresses critical limitations in existing anomaly detection methods by using a dual-channel architecture that separately processes trust and distrust signals to better identify Sybil attacks and exit scams.

• →TAS-GNN introduces a topology-aware approach to detect fraud in Bitcoin Web of Trust networks where traditional statistical methods fail.
• →The framework uses dual-channel message-passing to separately model trust and distrust signals, addressing semantic inversion issues in signed networks.
• →Current anomaly detection methods cannot distinguish between victims of bad-mouthing attacks and actual fraudsters in pseudonymous networks.
• →The system integrates recursive Web-of-Trust labeling with a Status-Aware Attention mechanism for improved accuracy.
• →Experimental results show TAS-GNN significantly outperforms existing signed GNN baselines in detecting adversarial behaviors.