LATIDIA · Ciberseguridad

Modelos de lenguaje grandes para el análisis de transacciones de criptomonedas: un estudio de caso de Bitcoin

arXiv: 2501.18158v5Tipo de anuncio: reemplazar Resumen: El análisis de transacciones de criptomonedas a menudo se basa en modelos de aprendizaje automático de caja negra que logran un alto rendimiento predictivo pero ofrecen una capacidad de interpretación limitada de tra

La noticia

arXiv:2501.18158v5 Announce Type: replace Abstract: Cryptocurrency transaction analysis often relies on black-box machine learning models that achieve high predictive performance but offer limited interpretability of transaction behaviors. This paper investigates the capabilities of large language models (LLMs) in analyzing real-world Bitcoin transaction graphs through a three-level framework: foundational metrics, characteristic overview, and contextual interpretation. To address token constraints, we introduce LLM4TG, a compact, human-readable graph representation, and CETraS, a connectivity-enhanced graph sampling algorithm. Experiments across five LLMs show that node-level information extraction achieves over 98.50% accuracy on most metrics, while meaningful graph characteristics are identified in up to 95.00% of responses. For address classification with limited labeled examples, top-1 accuracy