Linking Cryptoasset Attribution Tags to Knowledge Graph Entities: An LLM-based Approach
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929715856539648 |
|---|---|
| author | Avice, Régnier Haslhofer, Bernhard Li, Zhidong Zhou, Jianlong |
| author_facet | Avice, Régnier Haslhofer, Bernhard Li, Zhidong Zhou, Jianlong |
| contents | Attribution tags form the foundation of modern cryptoasset forensics. However, inconsistent or incorrect tags can mislead investigations and even result in false accusations. To address this issue, we propose a novel computational method based on Large Language Models (LLMs) to link attribution tags with well-defined knowledge graph concepts. We implemented this method in an end-to-end pipeline and conducted experiments showing that our approach outperforms baseline methods by up to 37.4% in F1-score across three publicly available attribution tag datasets. By integrating concept filtering and blocking procedures, we generate candidate sets containing five knowledge graph entities, achieving a recall of 93% without the need for labeled data. Additionally, we demonstrate that local LLM models can achieve F1-scores of 90%, comparable to remote models which achieve 94%. We also analyze the cost-performance trade-offs of various LLMs and prompt templates, showing that selecting the most cost-effective configuration can reduce costs by 90%, with only a 1% decrease in performance. Our method not only enhances attribution tag quality but also serves as a blueprint for fostering more reliable forensic evidence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10453 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Linking Cryptoasset Attribution Tags to Knowledge Graph Entities: An LLM-based Approach Avice, Régnier Haslhofer, Bernhard Li, Zhidong Zhou, Jianlong Cryptography and Security Artificial Intelligence Computation and Language Databases Machine Learning Attribution tags form the foundation of modern cryptoasset forensics. However, inconsistent or incorrect tags can mislead investigations and even result in false accusations. To address this issue, we propose a novel computational method based on Large Language Models (LLMs) to link attribution tags with well-defined knowledge graph concepts. We implemented this method in an end-to-end pipeline and conducted experiments showing that our approach outperforms baseline methods by up to 37.4% in F1-score across three publicly available attribution tag datasets. By integrating concept filtering and blocking procedures, we generate candidate sets containing five knowledge graph entities, achieving a recall of 93% without the need for labeled data. Additionally, we demonstrate that local LLM models can achieve F1-scores of 90%, comparable to remote models which achieve 94%. We also analyze the cost-performance trade-offs of various LLMs and prompt templates, showing that selecting the most cost-effective configuration can reduce costs by 90%, with only a 1% decrease in performance. Our method not only enhances attribution tag quality but also serves as a blueprint for fostering more reliable forensic evidence. |
| title | Linking Cryptoasset Attribution Tags to Knowledge Graph Entities: An LLM-based Approach |
| topic | Cryptography and Security Artificial Intelligence Computation and Language Databases Machine Learning |
| url | https://arxiv.org/abs/2502.10453 |